Control system for movement reconstruction and/or restoration for a patient

Abstract

A control system for a movement reconstruction and/or restoration system for a patient, comprising at least one sensor, at least one controller, at least one programmer, at least one stimulation system,
wherein the controller is connected with the sensor, the programmer and the stimulation system,
wherein the sensor is part of or attached to a training entity in order to create and/or guide a movement model for a patient and/or adjust stimulation settings based on sensor input.

Claims

1. A control system for a movement reconstruction and/or restoration system for a patient to support the patient's own natural control loop in determining movement cadence without forcing motion, comprising: at least one sensor; at least one controller; at least one programmer; at least one stimulation system; wherein the controller is connected with the at least one sensor, the at least one programmer, and the at least one stimulation system; wherein the at least one sensor is configured to be a part of or attached to a training entity in order to: create and/or guide a movement model for a patient; or adjust stimulation settings based on sensor input; wherein the at least one stimulation system is configured based on measured sensor data of a minimum of one complete movement cycle of the patient, the movement has a regular and characteristic pattern for a healthy subject.

2. The control system of claim 1, wherein the training entity is a trainer and/or physiotherapist.

3. The control system of claim 1, wherein the training entity is or comprises a training apparatus, wherein the apparatus is at least one of an exoskeleton, a robot, a treadmill, a cycling machine and/or a body weight support system.

4. The control system of claim 1, wherein the controller is configured and arranged for tracking and estimating the training entity movement and for translating it into stimulation data, based on the estimated movement, being provided by the stimulation system to the patient for the patient training for movement reconstruction and/or restoration.

5. The control system of claim 4, wherein the controller is configured and arranged so that the tracking and estimating is performed online and/or offline.

6. The control system of claim 4, wherein the controller is configured and arranged that the tracking and estimating is performed online and/or in real-time and/or with time delay.

7. The control system of claim 4, wherein the controller is configured and arranged so that tracking and estimating is performed from one patient to another patient.

8. The control system of claim 1, further comprising a sensor network formed from more than one of the at least one sensor, wherein the sensor network is connected to the controller.

9. The control system of claim 1, further comprising an augmented and/or virtual reality module, which is configured and arranged to provide information related to movement reconstruction and/or restoration, especially information related to the training to be performed or being performed for movement reconstruction and/or restoration.

10. The control system of claim 9, wherein the augmented and/or virtual reality module is configured and arranged to provide gamification information related to movement reconstruction and/or restoration.

11. The control system of claim 1, wherein the at least one sensor is or comprises at least one of an inertial measurement unit (IMU), an optical sensor, a camera, a piezo element, a velocity sensor, an accelerometer, a magnetic field sensor, a torque sensor, a pressure sensor, a displacement sensor, an EMG measurement unit, a goniometer, a magnetic position sensor, a hall sensor, a gyroscope and/or motion tracking video cameras, or infra-red cameras.

12. The control system of claim 1, wherein the training entity is the patient himself or herself.

13. The control system of claim 1, wherein the control system has a pre-warning module, which is configured and arranged to provide a pre-warning signal indicative of providing an upcoming stimulation event.

14. A method for movement reconstruction, comprising: responsive to detection of motion by at least one sensor coupled to a training entity: receiving a signal from the at least one sensor at a controller, the controller coupled to a programmer; generating stimulation instruction by the programmer based on the signal, the signal includes measurements recorded during at least one complete movement cycle of a patient, the movement has a regular and characteristic pattern for a healthy subject; commanding generation of stimulation pulses at the controller based on the stimulation instructions provided by the programmer; receiving the stimulation pulses at a pulse generator; transmitting the stimulation pulses to the patient through electrical leads connected to the pulse generator to support the patient's own natural control loop in determining movement cadence without forcing motion.

15. The method of claim 14, wherein detection of motion by at least one sensor includes attaching the at least one sensor to the patient's body and wherein the at least one sensor is included in a sensor network when more than one of the at least one sensor is connected to the controller.

16. The method of claim 14, wherein further comprising receiving data at the controller from the training entity and wherein the training entity is an entity separate from the patient and configured to define movement of the patient.

17. The method of claim 14, wherein generating stimulation instructions by the programmer includes receiving the signal from the at least one sensor at the programmer via the controller, adjusting stimulation parameters of a task based on the signal and sending the stimulation instructions to the controller through a communication link and wherein the programmer is a mobile device installed with applications.

18. The method of claim 14, wherein transmitting the stimulating pulses to the patient includes attaching the electrical leads to regions of the patient where stimulation is desired.

19. The method of claim 18, wherein the pulse generator is implanted subcutaneously in the patient and wherein transmitting the stimulation pulses to the patient provides epidural electrical stimulation.

20. The method of claim 14, further comprising updating a movement model implemented at the programmer, wherein the movement model is trained based on data generated from movement reconstruction of more than one patient.

Description

BRIEF DESCRIPTION OF THE FIGURES

(1) Further details and advantages of the present invention shall now be disclosed in connection with the drawings.

(2) It is shown in

(3) FIG. 1 a schematic, very simplified representation of a stimulation pulse delivered by a system according to the present invention;

(4) FIG. 2A, B the necessary current and necessary charge to trigger an action potential in a nerve fiber as a function of the pulse width (using a square pulse);

(5) FIG. 3 a table specifying the fiber types, diameter, and function;

(6) FIG. 4 the relationship between response delay and inter-muscle response delays;

(7) FIG. 5 a table specifying the intended movement and the involved agonist muscle and the involved antagonist muscle;

(8) FIG. 6 discrete sets of functional muscle blocks (FMB) and custom muscle blocks (CMB);

(9) FIG. 7 a general layout of an embodiment of a control system for a movement reconstruction and/or restoration system for a patient according to the present invention;

(10) FIG. 8A a schematical drawing of a patient equipped with an exoskeleton in connection with the embodiment disclosed in FIG. 7 according to the present invention;

(11) FIG. 8B a perspective view of a patient equipped with the control system disclosed in FIG. 7 comprising two sensors according to the present invention;

(12) FIG. 8C a perspective view of a patient equipped with the control system disclosed in FIG. 7 comprising seven sensors;

(13) FIG. 8D a perspective view of a sensor insole according to the present invention; and

(14) FIG. 8E a perspective view of a patient equipped with the control system disclosed in FIG. 7 comprising one IMU and one pressure insole for each foot according to the present invention.

(15) FIG. 9 a schematical view of a patient and a trainer (rehabilitation specialist) according to the present invention;

(16) FIG. 10 a schematical view of a patient and a remote trainer according to the present invention;

(17) FIG. 11 a flow chart of the offline workflow a control system according to the present invention;

(18) FIG. 12 a flow chart of the online workflow of a control system according to the present invention; and

(19) FIG. 13 a schematical diagram of food pitch/forward acceleration of a patient equipped with the control system disclosed in FIG. 7.

DETAILED DESCRIPTION

(20) Note that in the following we primarily refer to CNS/EES stimulation. The one skilled in the art may transfer the stimulation parameters to PNS/FES stimulation.

(21) The control system may provide stimulation data for movement reconstruction and/or restoration for stimulation of afferent nerve fibers using electrical current pulses. Given this starting point, the following stimulation parameters may be identified:

(22) Electrode configuration (which electrodes to use, polarity)

(23) Stimulation (Pulse) amplitude

(24) Stimulation (Pulse) width

(25) Stimulation (Pulse) frequency

(26) FIG. 1 illustrates a schematic, very simplified representation of the stimulation pulse, which illustrates the pulse amplitude, pulse width, and pulse frequency. Each stimulation pulse is followed by a neutralization pulse or a neutralization period (not depicted) to remove the electric charge from the tissue in order to avoid tissue damage.

(27) The effects of each of the stimulation parameters are described below.

(28) Electrode configuration: Stimulating a specific muscle group requires applying a specific electrical field at a specific location on the spinal cord or directly through stimulation of motorfibers (neuro-muscular stimulation), or through a limited set reflexes or by transcutaneously stimulating peripheral nerves. Therefore, in the present control system the electrical stimulation may be delivered e.g. to the spinal cord by a lead with multiple electrodes. The location, shape, and direction of the electrical field that is produced may be changed by choosing a different electrode configuration (which electrodes are used, with which polarity and potential) that is used to deliver the current. Hence, the electrode configuration may determine e.g. to which spinal roots the stimulation is delivered, and therefore which subsequent muscles or muscle groups activity will be reinforced.

(29) Pulse amplitude and pulse width: In FIG. 2A and FIG. 2B the necessary current and necessary charge to trigger an action potential in a nerve fiber are shown as a function of the pulse width (using a square pulse) (cf: Merrill D R., et al. Electrical Stimulation of excitable tissue: design of efficacious and safe protocols, J Neurosci methods 141(2):171-98 (2005)). FIG. 2A and FIG. 2B also show the rheobase current I.sub.rh, which is the current that is required when using infinitely long pulse widths, and the chronaxie time t.sub.c, which is the required pulse width at a current of 2I.sub.rh.

(30) Although larger currents may be required at smaller pulse widths, the total required charge may decrease with decreasing pulse width, see FIG. 2B. Hence shorter pulses with higher current amplitudes may be energetically beneficial.

(31) For smaller diameter nerves, the current-pulse width curve of FIG. 2A shifts, as smaller diameter fibers may require higher currents. Hence, a higher current may activate more nerve fibers, as also smaller diameter nerve fibers may be activated (until saturation). However, also cross-talk is increased as also more neurons from neighboring roots may be activated. Fortunately, the afferent fibers involved in motor control (fiber types Ia and Ib) may be all relatively large (12-20 μm), while the fibers involved in touch, temperature, and pain feedback (which should not be triggered) may be relatively small (0.5-12 μm), as depicted in FIG. 3. Hence, with increasing pulse width and/or current amplitude, the type Ia and Ib fibers may be the first to be recruited. This may enable recruiting (most of) the relevant fibers while keeping cross-talk and patient discomfort to a minimum.

(32) Pulse frequency: The pulse frequency may determine the frequency of the action potentials generated in the afferent nerves, assuming sufficient charge is delivered each pulse to trigger the action potentials. As no new action potential can occur in a nerve during the refractory period, the frequency of the triggered action potentials will saturate at high pulse frequencies. This saturation point is generally at around 200 Hz for afferent fibers (Miller J P., et al., Parameters of Spinal Cord Stimulation and Their Role in Electrical Charge Delivery: A Review. Neuromodulation: Technology at the Neural Interface 19, 373-384, (2016)). However, stimulation at frequencies above the saturation point may still be beneficial, as by increasing frequency the total charge delivered per unit time (i.e. charge per second) can be increased without changing current amplitude or pulse width (Miller J P., et al., Parameters of Spinal Cord Stimulation and Their Role in Electrical Charge Delivery: A Review. Neuromodulation: Technology at the Neural Interface 19, 373-384, (2016)).

(33) Pulse positioning: Many tasks, including walking, require simultaneous activation of multiple muscle groups. Hence, to support these tasks, multiple muscle groups may need to be stimulated simultaneously, each requiring a specific electrical field and pulse frequency. When applied simultaneously, these different electrical fields may interact with each other, potentially leading to unintended and uncontrolled effects. Therefore, to avoid this situation, care should be taken that the individual stimulation pulses and their neutralization periods targeting different muscle groups are not applied simultaneously. This may not be considered a stimulation parameter but does identify a required system feature: a pulse positioning algorithm.

(34) The previous section describes the effect of the stimulation parameters on triggering action potentials in afferent nerve fibers. Although triggering these action potentials is an essential step in the therapy, in the end the stimulation should enable or support the patient in performing specific lower body motions, which may require the activation of specific muscles or muscle groups. The effect of the triggered action potentials in afferent nerve fibers on muscle activation may be filtered inside the spinal cord through spinal reflex circuits and modulated through the voluntary control of the patient. Hence, the effect of the stimulation parameters on muscle activation may be not perfectly clear and may be affected by intra- and inter-Patient variations. The following aspects may be of relevance here:

(35) Different patients may have different levels of voluntary control over their lower body, depending on the type and severity of their SCI lesion level and state of (spontaneous) recovery.

(36) Stimulation of afferent nerve fibers may assist or enable activation of the corresponding muscles but may not necessarily enforce motion. The patient may modulate the activation (e.g. make a large or small step without changing the stimulation), or even resist motion of the leg completely. This may vary per patient and may change with increasing recovery.

(37) Conjecture: Because the spinal cord floats in the cerebrospinal fluid, the distance between the spinal cord and the lead electrodes may vary (mostly as a function of the patient's posture: prone—large distance, supine—small distance). Another hypothesis may be that due to posture changes, the layer thickness of low conductive epidural fat between the lead electrodes and the dura/cerebrospinal fluid a changing, leading to an impedance change as seen by the electrodes, and resulting in an altered current/voltage delivered stimulation by the electronics. As a result, the effect of the applied stimulation (including muscle onset and saturation) may also vary with the patient's posture. Although this conjecture is not proven, patients may successfully make use of the described effects to modulate the stimulation intensity by varying their posture: bending forward reduces the intensity, bending backward increases it.

(38) Pulse frequencies between 40 and 120 Hz may mostly be used, although it may theoretically be possible to stimulate up to 500 Hz as this may have benefits for selectivity in muscle activation and improved voluntary control of the patient.

(39) It may be possible that generally increasing the pulse amplitude may not lead to increased recruitment of muscle fibers (with corresponding increased cross-talk), and that increasing the stimulation frequency may lead to increased muscle activation without affecting cross-talk. However, increasing the stimulation frequency may reduce the intensity of natural proprioception and result in a decreased feeling in the leg of the patient. This is probably due to the collision of natural sensory inputs with antidromic action potentials generated by the electrical stimulation. At high frequency (above 100 Hz), patients may even report a complete loss of sensation of the leg and “feel like walking with their legs being absent”. This is a non-comfortable situation requiring the patient to make a leap of faith at each single step, believing that the leg that he/she does not feel anymore will support him/her during the next stance phase. Adjusting the balance between stimulation amplitude and frequency may therefore be necessary to find the optimal compromise between cross-talk limitation and loss of sensation. Simulations suggest that a possible workaround may be to shift the stimulation domain to lower amplitudes and even higher frequency, such that with a minimal number of stimulated fibers the same amount of activity is triggered in the spinal cord. Such hypothesis requires validation via additional clinical data. Finally, it may also be identified that different patients require different stimulation, i.e. that the optimal frequency and amplitude settings may vary highly between patients. Hence, the relation between stimulation amplitude and frequency on muscle activation may be still for a large part unclear. Moreover, the optimal stimulation settings may vary during the day, the assistive device that is used (crutches, walker, etc.), over time with improved recovery, and with the goal of the training or activity.

(40) Timing: Apart from applying the correct electrical field at the right location on the spinal cord, they also may need to be applied at the correct moments in time and correctly sequenced. The relevant timing aspects that are identified are listed below.

(41) There is a delay from stimulation on the spinal cord to muscle activation (typical values in the order of 0-30 ms depending on the muscle, see FIG. 4, LVLat=left vastus lateralis, RVLat=right vastus lateralis, Lll=left iliopsoas, Rll=right iliopsoas, LRF=left rectus femoris, RRF=right rectus femoris, LST=left semitendinosus, RST=right semitendinosus, LTA=left tibialis anterior, RTA=right tibialis anterior, LMG=left medial gastrocnemius, RMG=right medial gastrocnemius, LSol=left soleus, RSol=right soleus, LFHL=left flexor halluces longus, RFHL=right flexor halluces longus).

(42) While EES enables patients to perform motions, the patient may need to be able to predict when the stimulation will occur in order to make the best use of the stimulation. Likewise, suppressing motion while stimulation is provided also requires that the patient knows when to expect the stimulation. Hence, predictability of the stimulation timing is essential.

(43) When the stimulation is not synchronized to the patient's (intended) motion, the patient may not be able to perform a proper movement. Here, this may mean that the stimulation needs to be predictable by the patient, as the patient needs to synchronize to the stimulation.

(44) The duration of the stimulation for leg swing during walking may need to be finely tuned. For some patients, increasing the duration of this stimulation by 100 ms made the patient jump instead of performing a proper step.

(45) 20 ms may be a sufficient resolution for tuning the stimulation timings (i.e. the on/off times of the stimulation for a specific muscle group may not need to be controlled at a precision below 20 ms). Given current data availability, controlling the timings at resolutions below 20 ms may not seem to improve the effectiveness of the stimulation.

(46) Based on the previous sections, the stimulation parameters may be selected in the control system. This may determine the control output space that is used, and therefore the complexity of the control problem and the potential effectiveness of the control system.

(47) First it is discussed which parameter spaces can be reduced or eliminated. The remaining control output space is summarized below.

(48) Electrode configuration: Walking, as well as other movements of the lower extremities, may be composed of well-coordinated flexion and extension of lower body joints by contraction of agonist muscles and relaxation of antagonist muscles. The specific set of agonist and antagonist muscles for joint specific flexion and extension may be grouped, and as the number of joints is limited, this means that only a small discrete set of muscle groups may be needed to be stimulated. For each joint flexion and extension, a Space Time Programmer (STP for programming space and time of stimulation) will support creating the optimal electrode configuration for activation of the agonist muscles while avoiding activation of the antagonist muscles (as well as avoiding activation of muscles on the contralateral side). This may be done in a procedure called the functional mapping. We define the Functional Muscle Blocks (FMB), as the resulting stimulation configurations for each specific muscle group. At least 12 specific FMBs have been identified for use the control system, these are listed in FIG. 5 with their corresponding agonists and antagonists.

(49) As knee flexion and hip extension both involve the semitendinosus, it is physically not possible to target knee flexion and hip extension separately. Therefore, FIG. 5 does not include knee flexion (this could be considered redundant to hip extension).

(50) Next to the 12 FMB listed in FIG. 5, it is also envisioned that the trainer/therapist/physiotherapist may create Custom Muscle Blocks (CMB). Creating CMB may be useful in case the trainer/therapist/physiotherapist wants to apply stimulation that does not specifically target any of the 12 muscle groups targeted by the FMB, or in case the trainer/therapist/physiotherapist wants to use a variant of one of the 12 FMB in a specific task.

(51) Hence, by limiting the electrode configurations to the discrete set of FMB and CMB (versus an infinite number of possible electrode configurations), the control problem complexity may be reduced considerably without significantly affecting the potential effectiveness of the control system. Stimulation for a Task is then reduced to stimulation of (a subset of) the predefined FMB and CMB, see FIG. 6. For this example, the Right Trunk Stability is used in both Task 1 and Task 2.

(52) The functional mapping procedure may require measuring the response of each of the muscles listed in FIG. 5 with EMG sensors. Due to the large number of muscles, this requires attaching many EMG sensors to the patient (which is time consuming) and processing a large amount of data. Moreover, as motion of the patient may induce signal artifacts, the functional mapping may be best performed while the patient is not moving. For these reasons, the functional mapping procedure may be performed in a separate session using a STP for programming space and time of stimulation, and not e.g. adaptively within the control system. Hence, the configuration of FMB and CMB may be considered as a given to the control system.

(53) Pulse width: From the viewpoint of triggering action potentials in afferent nerve fibers, the parameters pulse width and pulse amplitude may be tightly linked and may together determine which afferent nerve fibers are recruited. Increasing the pulse width may allow to reduce the amplitudes and decreasing the pulse width may allow reducing energy consumption (as the total required charge for triggering an action potential decreases with decreasing pulse width, see FIG. 2B) and stimulating more FMB simultaneously or at higher frequencies. However, from a control perspective the two parameters may be (almost) redundant, as increasing either parameter may lead to the recruitment of more afferent nerve fibers over a larger area.

(54) Pulse widths below chronaxie time t.sub.c may quickly require high currents (and thus high voltages), which is difficult to produce and may lead to patient discomfort. Beyond t.sub.c, the strength-duration curve of FIG. 2A is almost flat, so increasing pulse width beyond t.sub.c has little effect on the required amplitudes while it increases total power consumption. Also considering that having a fixed pulse width simplifies the pulse positioning, the pulse width is chosen to be fixed (at a value near chronaxie time t.sub.c such that both energy consumption and required current amplitudes remain low, where t.sub.c≈200 μs for afferent dorsal root nerve fibers in humans). This reduces the complexity of the control problem by reducing the number of output parameters.

(55) This may leave the following stimulation parameters to be controlled over time by the control system:

(56) Which FMBs to stimulate

(57) Stimulation amplitude per FMB

(58) Stimulation frequency per FMB

(59) The pulse positioning may be considered a lower level problem and may therefore be not a direct output of the control system (system feature). The pulse positioning will be performed by the IPG.

(60) Although combining amplitude and frequency to a single ‘intensity’ parameter has been considered, doing so may not be envisioned for the control system, as these parameters may have very different effects. On triggering action potentials in afferent nerve fibers, the amplitude and frequency may be independent parameters: the amplitude determines in which afferent nerve fibers action potentials are triggered, the frequency determines the rate at which they are triggered. Hence, in principle the amplitude determines which muscle fibers are activated, the frequency determines how hard, although it is unclear if the independence of the two parameters also holds for muscle activation due to the signal processing that occurs in the spinal cord. Moreover, it may be apparent that for some patients changing the amplitude gives the best results, while for other patients the frequency may be the more useful parameter.

(61) As the precise relation between frequency and amplitude is not known in the clinical context it may not be recommended to combine frequency and amplitude to single parameter. Hence, the stimulation frequency and amplitude may be controlled independently from each other.

(62) In the following the sensor, the controller, the programmer and the stimulation system (e.g. IPG) of the present invention are described in greater detail.

(63) Sensors: Battery powered, body worn sensors (directly or indirectly, and/or sensors placed on and/or integrated into one or more training entities), collecting motion data, and sending it to the controller. Its intended use is to capture body motion parameters.

(64) Controller: Battery powered, body worn device (directly or indirectly), receiving data from sensor(s) and able to send stimulation commands to the IPG for specific tasks (i.e. an activity/training exercise). Its intended use is to determine optimal stimulation settings for any given task and providing this information to the IPG. In addition, this device can take the IPG out of shelf mode, charge the IPG battery transcutaneous, and initiate an IPG-lead integrity test.

(65) Programmer: The programmer, or also called the clinician programmer, can be used to receive inter alia stimulation parameter, patient data, physiological data, training data etc.

(66) It may comprise a Space Time Programmer (STP) for e.g. programming space and time of the stimulation, a Physiotherapist Programmer (PTP) for e.g. allowing the physiotherapist adjustment to the stimulation, and a patient Programmer (PP) for e.g. allowing the patient to select a specific stimulation program.

(67) The Space Time Programmer (STP), Physiotherapist Programmer (PTP), and Patient Programmer (PP) can be embodied as applications installed on a mobile device that communicate with the controller. They are used by the treating physician (TP), a physiotherapist (PT), or the Patient to provide inputs to the controller, e.g., selecting, starting, and stopping a task or configuring stimulation parameters.

(68) The programmer can allow adjusting the stimulation parameters of a task, while the task is running. This enables the user to tune the stimulation without having to start and stop the task, which would be very cumbersome at the start of the rehabilitation training, when all stimulation partitures are developed and tuned.

(69) Generally speaking, the programmer may have the following structure:

(70) In a first embodiment, the programmer can be embodied such that it is possible to receive inter alia but not limited to stimulation parameters, patient data and the like, check and/or reprogram the stimulation data and send it back to e.g. the controller.

(71) The programmer is in this first embodiment capable to receive data from the implanted (part of the) system (e.g. the controller), display data, receive input from the user and then send it back to the controller. In other words: The programmer can receive, process and re-send the data.

(72) In a second embodiment, the programmer may receive data from a remote database. The database may be e.g. linked with the stimulation system via a separate interface, which is configured for data transfer from the system to the database only.

(73) The programmer is in this second embodiment capable to receive data from the remote database, display data, receive input from the user and then send it to the controller. In other words: The programmer is only in connection with the controller for sending data, it does not receive data from the controller or any implanted system parts.

(74) Stimulation system, here IPG: Implantable Pulse Generator. A battery powered device that generates the electrical stimulation, subcutaneously implanted. Its intended use is to deliver electrical stimulation to the lead based on command received from the controller.

(75) FIG. 7 shows a general layout of an embodiment of the control system 10 for a movement reconstruction and/or restoration system for a patient P according to the present invention.

(76) The control system 10 comprises one or more sensors 12, while two or more sensors could form a sensor network.

(77) Furthermore, the control system 10 comprises in the shown embodiment a controller 14.

(78) Additionally, the control system 10 comprises a programmer 16.

(79) There is also an implantable pulse generator (IPG) 18.

(80) In an alternative embodiment, the pulse generator can be also a non-implantable pulse generator.

(81) The control system may further comprise a lead 20.

(82) The lead 20 may be a connection cable (i.e. lead cable) with one or more electrodes.

(83) The one and more electrodes may be arranged on a lead paddle connected to the lead.

(84) In one embodiment, the controller 14 is body-worn, the programmer 16 is a mobile device, the IPG 18 is implanted in the body, and the one or more sensors 12 is/are attached to the patient's limbs/feet or to a training entity 22.

(85) The training entity 22 could be a bicycle.

(86) In one embodiment, the training entity 22 could be a trainer T and/or physiotherapist.

(87) The one or more sensors 12 is/are connected to the controller 14.

(88) The connection between the one or more sensors 12 and the controller 14 is a bidirectional connection.

(89) The connection between the one or more sensors 12 and the controller 14 is in the shown embodiment a direct connection.

(90) However, also an indirect connection (i.e. with another component of the control system 10 in between) would be generally possible.

(91) The connection between the one or sensors 12 and the controller 14 is established in the shown embodiment via a wireless network WSN.

(92) However, also a cable-bound connection would be generally possible.

(93) Moreover, the controller 14 is connected to the programmer 16, in the shown embodiment by means of a direct connection COM (also called “communication line”).

(94) However, also an indirect connection would be generally possible.

(95) The connection between the controller 14 and the programmer 16 is established in the shown embodiment via a wireless link.

(96) However, also a cable-bound connection would be generally possible.

(97) The controller 14 is connected to the IPG 18 in the shown embodiment via a direct connection.

(98) However, also an indirect connection (i.e. with another component of the control system 10 in between) would be generally possible.

(99) The connection between the controller 14 and the IPG 18 is established in the shown embodiment via a wireless link TEL.

(100) However, also a cable-bound connection would be generally possible.

(101) The IPG 18 is connected to the lead 20.

(102) By means of the one or sensors 12 signals indicative for a motion, e.g. movement of position of a limb, e.g. a foot or hand, or the trunk or the head or other parts of the body can be sensed and used by the control system 10.

(103) The sensor signals are transferred to the controller 14 and there processed.

(104) The controller 14 processes data that is from e.g. the sensor 12, the IPG 18, and the programmer 16.

(105) By means of the controller 14 the control software is executed.

(106) By means of the programmer 16 inputs to the controller 14, e.g., selecting, starting, and stopping a task or configuring stimulation parameters are provided.

(107) It is generally possible that the programmer 16 allows adjusting the stimulation parameters of a task, while the task is running.

(108) It is generally possible that the programmer 16 is used by a therapist, physiotherapist, or patient.

(109) The controller 14 programs the IPG 18 to deliver the correct stimulation via the lead 20.

(110) Via the lead 20 and the respective electrode(s) stimulation can be provided, here EES.

(111) Alternatively, also other suitable stimulation signals may be provided.

(112) In particular, also PNS stimulation could be provided.

(113) In particular PNS stimulation could be provided by an IPG 18.

(114) In general, the control system 10 creates and/or guides a movement model m for a patient and/or adjusts stimulation settings based on sensor 12 input.

(115) However, also an external stimulation system could be generally possible.

(116) Not shown in greater detail in FIG. 7 is the fact that the one or more sensors 12 is/are part of or attached to a training entity 22.

(117) In an alternative embodiment the training entity 22 could also be the patient P himself or herself

(118) It is also possible that the controller 14 tracks and/or estimates the movement of the training entity 22 for translating it into stimulation data, based on the estimated movement, being provided by the stimulation system 18 to the patient for the patient training.

(119) Not shown in FIG. 7 is that the control system 10 may comprise a pre-warning module, which is configured and arranged to provide a pre-warning signal indicative of providing an upcoming stimulation event.

(120) In particular, the pre-warning signal may act in a sub-motor threshold region at which a sensation is evoked, but not a motor response.

(121) Not shown in FIG. 7 is that the at least one sensor 12 is an inertial measurement unit (IMU).

(122) In an alternative embodiment, the at least one sensor 12 could also be an optical sensor, a camera, a piezo element, a velocity sensor, an accelerometer, a magnetic field sensor, a torque sensor, a pressure sensor, a displacement sensor, an EMG measurement unit, a goniometer, a magnetic position sensor, a hall sensor, a gyroscope and/or motion tracking video cameras, or infra-red cameras.

(123) Not shown in FIG. 7 is that the control system 10 could further comprise an augmented and/or virtual reality module, which is configured and arranged to provide information related to movement reconstruction and/or restoration, especially information related to the training to be performed or being performed for movement reconstruction and/or restoration.

(124) Further not shown in FIG. 7 is that the augmented and/or virtual reality module could be configured and arranged to provide gamification information related to movement reconstruction and/or restoration.

(125) Further not shown in FIG. 7 is that it could be generally possible that the controller 14 and/or the programmer 16 are integrated into the IPG 18 or vice versa. Further, it could be possible that the programmer 16 is integrated in the controller 14 or vice versa.

(126) In general, every single component of the control system 10 could be integrated in any other component of the control system 10.

(127) According to the state of the art, voluntary control of movement still cannot be achieved by the subject. It is important to keep in mind that the patient is not a robot and can and should not be stimulated and controlled as a robot. Therefore, there is a lack to have a system which overcomes the drawbacks of the prior art. In particular, there is the need of a system stimulating the patient not as a robot. The goal of applying stimulation is not to control the patient, but to support the patient during training and daily life activities.

(128) Hence, the control system 10 shall support the patient's own natural control loop composed of the brain, nervous system, and sensory organs. This means that said control system should not e.g. adjust the stimulation parameters to force the patient's lower body motion to a given reference trajectory. Instead, the patient should be able to determine e.g. the walking cadence.

(129) FIG. 8A shows a patient equipped with an exoskeleton in connection with the embodiment disclosed in FIG. 7 according to the present invention.

(130) In this embodiment, a patient P is equipped with said control system 10 disclosed in FIG. 7 and a training entity 22, in particular an exoskeleton 22a.

(131) The exoskeleton 22a in this embodiment is an external structure designed around the shape and function of the patient's P lower body, particularly the patient's P legs.

(132) However, in an alternative embodiment the exoskeleton 22a could also be designed around the patient's P trunk and/or neck and/or head and/or arms.

(133) In an alternative embodiment, the exoskeleton 22a could also be designed around the total body of the patient P.

(134) The one or more sensor(s) 12 is/are placed on the exoskeleton 22a to assess leg kinematics.

(135) In an alternative embodiment, the sensors 12 could also be integrated in the exoskeleton 22a.

(136) According to FIG. 7, by means of the one or more sensors 12 attached to the exoskeleton 22a signals indicative for a motion, e.g. movement of position of the patient's P body and/or one or more parts of the patient's P body, here a leg and/or a foot, can be sensed and used by the control system 10.

(137) The controller 14 tracks and/or estimates the movement of the exoskeleton 22a and translates it into stimulation data, based on the estimated movement, being provided by the stimulation system 18 to the patient for the patient training.

(138) In an alternative embodiment, remote control of the system and the exoskeleton 22a is possible.

(139) Not shown in greater detail in FIG. 8A is that other embodiments of the training entity 22 could generally comprise a robot, a treadmill, a cycling machine and/or a body weight support system or the like.

(140) Not shown in FIG. 8A is that the training entity 22 could also be the patient P himself or herself.

(141) FIG. 8B shows a perspective view of a patient P equipped with the control system 10 disclosed in FIG. 7 comprising two sensors 12 according to the present invention.

(142) In this embodiment, a patient P is equipped with said control system 10 disclosed in FIG. 7 comprising two sensors 12, which are here two IMUs 12a attached to the shoes S of the patient P.

(143) In particular, one IMU 12a is attached to the left shoe S of the patient P and one IMU 12a is attached to the right shoe S of the patient P.

(144) In this embodiment, the IMUs 12a are placed on the heel area of the shoes S of the patient P.

(145) In this embodiment, the control system 10 comprises also two electrodes 24a for FES.

(146) In particular, one electrode 24a for FES is attached to the left leg of the patient P and one electrode 24a for FES is attached to the right leg of the patient P.

(147) However, it could be generally possible that each leg of the patient P is equipped with two or more electrodes 24a for FES.

(148) In particular, one electrode 24a for FES is attached to the left upper leg of the patient P and one electrode 24a for FES is attached to the right upper leg of the patient P.

(149) However, it could be generally possible that the one or more electrodes 24a for FES are placed at any position(s) of the legs and/or hips and/or trunk of the patient P.

(150) Further, in this embodiment, the control system 10 comprises one electrode 24b for EES.

(151) The electrode 24b for EES is attached to the dorsal roots of the patient P.

(152) However, also positioning two or more electrodes 24b for EES to the dorsal roots, in the epidural space, or on top of the spinal cord could be generally possible.

(153) According to FIG. 7, by means of the two IMUs 12a attached to each shoe S of the patient P each movement of the left foot and right foot of the patient P is sensed and used by the control system 10.

(154) The controller 14 tracks and/or estimates the movement of the foot of the patient P for translating it into stimulation data, based on the estimated movement, being provided by the IPG 18 to the patient P.

(155) The IPG 18 provides FES via the lead 20 and the electrode module 24 with the one or more electrodes 24a.

(156) The IPG 18 provides EES via the lead 20 and the electrode module 24 with the one or more electrodes 24b.

(157) In an alternative embodiment, the IMUs 12a could be placed at and/or inserted in, and/or integrated in different positions in the shoe S or in the shoe sole and/or in the shoe insole.

(158) In an alternative embodiment, the control system 10 could comprise only one IMU 12a positioned directly or indirectly to the left foot or the right foot, or the left shoe S or the right shoe S of the patient P.

(159) Alternatively, a patient P equipped with the control system 10 disclosed in FIG. 7 could be equipped with two or more sensors 12 for each foot and/or leg, cf. also FIG. 8C.

(160) In particular, a patient equipped with the control system 10 disclosed in FIG. 7 could be equipped with more sensors 12 located on a chain, e.g. from hip to foot via thigh, knee and shank.

(161) In general, two or more sensors 12 can be located on a chain from head to toes.

(162) In particular, a shoe S and/or a shoe sole and/or a shoe insole could be equipped with two or more sensors 12.

(163) Said sensors 12 may be positioned at any place from the distal end to the proximal end of the foot, in particular in the heel area and/or the metatarsal area and/or the toe area, and/or the sides of the feet.

(164) In an alternative embodiment, the one or more sensor(s) 12 could be part of and/or inserted and/or integrated into and/or onto an exoskeleton, tights, a belt, straps, a stretching band, a knee sock, a sock and/or a shoe S of the patient.

(165) However, it could be generally also possible that socks and tights consist of or comprise a piezoelectric textile sensor integrated in the trunk, waist, hip, knee, heel and/or toe area.

(166) An electrical response according to a mechanical stretching, pressing or pulling could be delivered.

(167) In particular, socks or tights could be equipped with electrodes and/or electro conductive yarn.

(168) Alternatively, magnetic sensors and magnetic field sensors could be incorporated in shoes S for walking on a magnetic sensor plate or inserted in the treadmill or gait phase detection device.

(169) The magnetic force could be detected and acquired by magnetic sensors under training, e.g. gait training.

(170) Not shown in FIG. 8B is that for assessing upper body motion and/or arm motion and/or hand motion, the one or more sensors 12 could be inserted and/or integrated into and/or onto clothing or the like for the upper body, the trunk and/or arms, and or hands, including but not limited to a top, a longsleeve, a pullover, a jacket, one or more arm sleeves, gloves, and/or one or more armlets.

(171) Not shown in FIG. 8B is that the electrodes 24a for FES could also be configured and arranged for foot and/or leg cramp stimulation to release cramp and/or detection of foot and/or leg cramp.

(172) Not shown in FIG. 8B is that stimulating motion of one or more limbs and/or one or more parts of a limb does not necessarily require stimulating on the locomotor system of one or more limbs and/or one or more parts of the limb, respectively, directly.

(173) As just one example, the spinal cord or the upper leg may be stimulated to induce a reflex and/or motion of the foot.

(174) FIG. 8C shows a perspective view of a patient equipped with the control system 10 disclosed in FIG. 7 comprising seven sensors 12.

(175) In this embodiment, a patient P is equipped with said control system 10 disclosed in FIG. 7 comprising seven sensors 12, which are here seven IMUs 12a.

(176) The seven IMUs 12a build a sensor network 12c.

(177) In this embodiment, the seven IMUs 12a are attached to the lower body of the patient P.

(178) In particular, one IMU 12a is placed centrally in the hip area, whereas the left leg is equipped with three IMUs 12a placed on the foot, the lower leg, and the upper leg, and whereas the right leg is equipped with three IMUs 12a, placed on the foot, the lower leg, and the upper leg, respectively.

(179) However, also alternative placements of the IMUs 12a along the legs and/or feet and/or the lower body could be generally possible.

(180) In general, also alternative placements of the IMUs 12a, or other sensor 12 types, along the body and/or parts of the body, e.g. the head, the neck, the trunk and/or one or both arms and/or one or both hands could be generally possible.

(181) According to FIG. 7, by means of the seven IMUs 12a placed on the lower body of the patient P each movement of the legs and feet of the patient P is sensed and used by the control system 10.

(182) According to FIG. 8B, both FES and EES can be provided by the IPG 18, the lead 20 and the electrode module 24 with respective electrodes 24a and 24b.

(183) FIG. 8D shows a perspective view of a sensor insole according to the present invention.

(184) In this embodiment, according to the control system 10 disclosed in FIG. 7, various sensors 12 are integrated into a sensor insole 300 of a shoe S of a patient P.

(185) In this embodiment, the sensors 12 are pressure sensors 12b.

(186) In particular, eight pressure sensors 12b are incorporated in a sensor insole 300 of a shoe S of a patient P.

(187) In particular, the eight pressure sensors 12b are distributed from the distal end di of a sensor insole 300 to the proximal end pr of a sensor insole 300 of a shoe S of a patient.

(188) In particular, the eight pressure sensors 12b are distributed along the heel area, the metatarsal area, and the toe area of the sensor insole 300.

(189) In particular, two pressure sensors 12b are placed in the heel area, two pressure sensors 12b are placed in the toe area and four pressure sensors 12b are placed in the metatarsal area of the sensor insole 300.

(190) In general, both shoes S of a patient P could be equipped with sensor insoles 300.

(191) The sensor insoles 300 provide a precise map of the foot force.

(192) In particular, the pressure sensors 12b in the sensor insole 300 provide a precise description of the gait phase and cadence, e.g. pre-swing, swing, loading response and/or stance (or alternatively swing, stance, toe-off, midswing, heel strike, flat foot, midstance and/or heel-off) can be identified for one foot by analyzing sensor data obtained from one sensor insole 300 of a shoe S.

(193) The same events and parameters can be identified for the other foot of the patient P by using a second sensor insole 300.

(194) By combining signals of sensor insoles 300 of both feet of a patient P, together with the gait phase and cadence of the stimulation input, a reliable gait phase and cadence estimate can be provided.

(195) The sensor stream is transmitted to the controller 14 according to the disclosure of FIG. 7.

(196) In one embodiment, alternative placements of the eight pressure sensors 12b in a sensor insole 300 could be possible.

(197) However, it could be also possible that 1-7 or more than 8 pressure sensors 12b are integrated in a sensor insole 300 of a shoe S of a patient P.

(198) It could also be possible that the sensor insole 300 itself is a pressure sensor 12b.

(199) FIG. 8E shows a perspective view of a patient equipped with the control system disclosed in FIG. 7 comprising one IMU and one pressure insole for each foot of the patient according to the present invention.

(200) In this embodiment, a patient P is equipped with the control system 10 disclosed in FIG. 7 including one IMU 12a placed on the left shoe S and one IMU 12a placed on the right shoe S of a patient P as disclosed in FIG. 8B and one sensor insole 300 as disclosed in FIG. 8D for the left shoe S of the patient P and one sensor insole 300 as disclosed in FIG. 8D for the right shoe of the patient P.0

(201) Accordingly, the sensor insoles 300 for both shoes of the patient P comprise eight pressure sensors 12b (only exemplarily shown in FIG. 8D).

(202) Alternatively, a patient P could be equipped with the control system 10 described in FIG. 7 including one IMU 12a and one respective sensor insole 300 for the left or the right foot.

(203) In another embodiment, the IMU 12a and/or the sensor insole 300 can be replaced by another type of sensor 12 including but not limited to e.g. a piezo element.

(204) In this embodiment, it could be possible that the piezo element is integrated in wearables like e.g. a sock, a knee sock, tights, a shoe.

(205) FIG. 9 shows a schematical view of a patient P and a trainer T (rehabilitation specialist) according to the present invention.

(206) In this embodiment, the patient P and the trainer T are each equipped with one control system 10 disclosed in FIG. 7.

(207) In this embodiment, the control system 10 of the patient P and the control system 10 of a trainer T are interconnected.

(208) The connection between the control system 10 of the patient P and the control system 10 of the trainer T is established by a wireless link WL.

(209) However, also a cable-bound connection would be generally possible.

(210) By means of a wireless link WL between the control system 10 of the patient P and the control system 10 of the trainer T reference data from the control system 10 of the trainer T are copied to the control system 10 of the patient P.

(211) In particular, by means of a wireless link WL between the control system 10 of the patient P and the control system 10 of the trainer T the timing of stimulation of patient P is synchronized to the motion(s) of trainer T.

(212) However, also other reference data, including but not limited to step high or step size could generally be transferred from the control system 10 of the trainer T to the control system 10 of the patient P.

(213) In particular, the control system 10 of the trainer T functions as reference for open-loop stimulation of the patient P by the control system 10 of patient P.

(214) Alternatively, the control system 10 of trainer T could function as reference for closed-loop stimulation of the patient P by the control system 10 of patient P.

(215) Note that different gait events (toe-off, midswing, heel strike, flat foot, midstance and/or heel-off, or alternatively pre-swing, swing, loading response and/or stance) can be synchronized between the trainer T and the patient P.

(216) However, also for movements other than gait, e.g. cycling, swimming, rowing, standing up, sitting down, different movement events can be synchronized between the trainer T and the patient P

(217) However, in an alternative embodiment it could be generally possible that data are transferred offline and with time-delay.

(218) Note that said synchronization could enable identifying and/or evaluating and/or correcting for the difference(s) between the healthy, regular and physiological movement of the trainer T and the impaired and irregular movement of the patient P.

(219) Further, synchronizing a control system 10 of a patient P more advanced in the rehabilitation process to the control system 10 of a patient P less advanced in the rehabilitation process would be generally possible.

(220) However, also partially or totally tracking and estimating control algorithms and/or movement model from the control system 10 of the patient P to the control system 10 of the trainer T is generally possible.

(221) Further, also synchronizing and/or partially or totally tracking and estimating control algorithms and/or movement model from a control system 10 of a patient P more advanced in the rehabilitation process to the control system 10 of a patient P less advanced in the rehabilitation process would be generally possible.

(222) The tracking and estimating could be performed online and/or in real-time and/or with time delay.

(223) However, in an alternative embodiment also tracking and estimating offline could be generally possible.

(224) Not shown in FIG. 9 is the fact that the patient P, the trainer T or the one or more further patients could be equipped with a training apparatus, e.g. an exoskeleton 22a, a robot, a treadmill, a cycling machine and/or a body weight support system or the like, as disclosed in FIG. 8A.

(225) FIG. 10 shows a schematical view of a patient P and a remote trainer T1 according to the present invention.

(226) In this embodiment, a patient P is equipped with said control system 10 disclosed in FIG. 7 and located at location L.

(227) In this embodiment, a remote trainer T1 is equipped with said control system 10 disclosed in FIG. 7 and located at location L1 remote from the location L of the patient P.

(228) The control system 10 of a patient P and the control system 10 of a remote trainer T1 are interconnected.

(229) The connection between the control system 10 of the remote trainer T1 and the control system 10 of the patient P is established by a wireless link WL.

(230) By means of a wireless link WL between the control system 10 of the patient P and the control system 10 of the remote trainer T1 it is possible that control algorithms from the controller 14 of the control system 10 of the remote trainer T1 are copied to the controller 14 of the control system 10 of the patient P.

(231) However, also copying control algorithms from the controller 14 of the control system 10 of one remote trainer T1 to the controller 14 of the control system 10 of two or more patients P located in different locations is possible.

(232) It is also possible that the two or more patients differ in terms of progress in the rehabilitation process.

(233) In this embodiment, the tracking and estimating is performed online and in real-time.

(234) However, also tracking and estimating offline and with time-delay could be possible.

(235) Not shown in FIG. 10 is that it could be generally possible, that the one or more patients P watch the remote trainer T1 and vice versa—via e.g. a standard screen, a beamer, a computer, a laptop, a tablet computer, or a mobile phone.

(236) It could also be possible that the patient P and the remote trainer T1 communicate with each other via a general telecommunication device.

(237) Not shown in FIG. 10 is that the controller may in general allow that tracking and estimating is performed from one patient to another patient.

(238) Not shown in FIG. 10 is that it could be generally possible, that the one or more patients P and the remote trainer T1 communicate within an augmented and/or virtual reality module as described for the embodiment in FIG. 7.

(239) In this regard, also gamification is possible.

(240) FIG. 11 shows a flow chart of the offline workflow of a control system for a movement reconstruction and/or restoration system for a patient according to the present invention.

(241) It is applicable, inter alia, to all described embodiments of the invention described in this disclosure.

(242) The offline workflow 100 for the control system 10 for a gait reconstruction and/or restoration system for a patient P as disclosed in FIG. 7 and FIG. 8A comprises the steps S101-S106.

(243) In starting step S101 the one or more sensors 12 or the one or more sensor networks measure sensor data for a period of time of minimum one complete movement cycle.

(244) In one embodiment, the movement cycle could be a gait cycle.

(245) In an alternative embodiment, the movement cycle could be a swim or row cycle, or standing up, or sitting down.

(246) In an alternative embodiment, the movement cycle could be any other movement.

(247) In step S102 the sensor data are transferred to the controller 14.

(248) In step S103, accumulated sensor data for the recorded period of time are stored in the sensor data buffer of the controller 14.

(249) After that, in step S104, based on the accumulated sensor data for the recorded period of time in the sensor data buffer, the controller 14 determines a list of different movement events and phase offline.

(250) For gait, possible gait events could include but are not limited to initial ground contact, heel strike, foot flat, loading response, midstance, terminal stance, heel off, preswing, toe off, initial swing, midswing, terminal swing, and/or heel strike (or e.g. pre-swing, swing, loading response, stance).

(251) However, it could be possible that there are only two gait events, foot-strike and foot-off.

(252) After the determination of a list of different movement events and phase offline in step 104, a movement model for the recorded movement events is created in step S105.

(253) After that, in step S106 stimulation of the patient is performed.

(254) It could be possible to use the created movement model offline at any time.

(255) The controller 14 programs the IPG 18 to deliver the correct stimulation via the lead 20 according to the movement model determined offline by the controller 14.

(256) According to the movement model determined offline the movement phase always takes the same value at the same event.

(257) Performing the tracking and estimating offline may allow to use criteria that could not be used on real-time.

(258) Note that it is possible that the sensor data buffer of the controller 14 could comprise accumulated sensor data from one patient P, and/or from two or more patients P.

(259) However, it is also possible that the sensor buffer could comprise accumulated sensor data from one or more trainers T and/or one or more healthy subjects.

(260) Not shown in FIG. 11 is that recorded sensor data could be preprocessed using a Kalman filter.

(261) FIG. 12 shows a flow chart of the online workflow of a control system for a movement reconstruction and/or restoration system for a patient according to the present invention.

(262) It is applicable, inter alia, to all described embodiments of the invention described in this disclosure.

(263) The online workflow 200 for the control system 10 for a movement reconstruction and/or restoration system for a patient P as disclosed in FIG. 7 and FIG. 8A comprises the steps S201-S206.

(264) In starting step S201 one or more sensors 12 or one or more sensor networks measure sensor data.

(265) In step S202 the sensor data are transferred from the sensor 12 to the sensor data buffer of the controller 14.

(266) In step S203 sensor data for the recorded period of time are stored online in the sensor data buffer of the controller 14.

(267) In other words, the sensor data buffer is always updated online by recent sensor data from the sensor(s) 12.

(268) Based on a general movement model and accumulated sensor data in the sensor data buffer of the controller 14, in step S204, the controller 14 determines a list of different movement events and phase for all recorded movement events.

(269) For gait, possible movement events, gait events, respectively, could include but are not limited to initial ground contact, heel strike, foot flat, loading response, midstance, terminal stance, heel off, preswing, toe off, initial swing, midswing, terminal swing, and/or heel strike.

(270) However, it could be possible that there are only two gait events, foot-strike and foot-off.

(271) Various sensor data inputs from the sensor(s) 12 update the sensor data buffer and as soon as a whole movement, e.g. gait cycle, is detected, the past movement event, e.g. gait event, is determined online.

(272) In step 205 the controller 14 trains the movement model using recent accumulated sensor data to adapt the particular movement of the patient P.

(273) In step S206 stimulation of the patient P is performed according to the movement model.

(274) The controller 14 programs the IPG 18 to deliver the correct stimulation via the lead 20 according to the recent movement model determined online by the controller 14.

(275) The online workflow 200 realizes a real-time solution and a real-time data transfer.

(276) Note that it is possible that the general movement model used for fusing with recent sensor data could be based on accumulated sensor data from one patient P, and/or from two or more patients P.

(277) However, it is also possible that the general movement model used for fusing with recent sensor is based on sensor data from one or more trainers T and/or one or more healthy subjects.

(278) It could be possible to stop the online learning process when the movement model is good enough and to store it for further sessions with the same patient P.

(279) Not shown in FIG. 12 is that recorded sensor data could be preprocessed using a filter.

(280) Not shown in FIG. 12 is that the filter could be a Kalman filter.

(281) However, also other types of filters could be generally used to preprocess recorded sensor data.

(282) Not shown in FIG. 12 is that the online workflow 200 could also be used for a control system 10 for a movement reconstruction and/or restoration system for diverse movements including e.g. walking, running, cycling, swimming, rowing, standing up, sitting down.

(283) FIG. 13 shows a schematical diagram of foot pitch/forward acceleration of a patient P equipped with the control system disclosed in FIG. 7.

(284) Here, the patient P is equipped with one IMU 12a per foot.

(285) Alternatively, the patient P could be equipped with the control system 10 described in FIG. 7 including one IMU 12a and one respective sensor insole 300 for the left or the right foot.

(286) In another embodiment, the patient P could be equipped with two or more IMUs 12a per foot.

(287) Further, the IMU 12a and/or the sensor insole 300 can be replaced by another type of sensor 12 including but not limited to e.g. a piezo element.

(288) In this embodiment, it could be possible that the piezo element is integrated in wearables like e.g. a sock, a knee sock, tights, a shoe.

(289) The foot pitch (degree) and forward acceleration (meter per s.sup.2) of the right foot of a patient P equipped with the control system 10 disclosed in FIG. 7 during walking is shown.

(290) From these signals, clearly the cadence, pre-swing, swing, loading response and stance can be identified.

(291) The same events and parameters can be identified for the left foot.

(292) As walking is a periodic motion, all measured signals are also periodic.

(293) By combining gait phase and cadence information of both feet of the patient P together with the gait phase and cadence of the stimulation input, a reliable gait phase and cadence estimate can be provided.

(294) Note that gait can vary a lot between different patients P as well as for a single patient P for different walking speeds and different assistive devices (body-weight support, walker, crutches, etc.).

(295) Especially for impaired gait, not all gait events are always present.

(296) Hence, it is always possible to estimate the cadence by extracting the base frequency of the measured signals.

(297) Moreover, machine-learning methods can be used to adapt the gait phase estimation to the specific gait of the patient P.

(298) The level of agreements and discrepancies between motion of the left and right foot, and the stimulation input, can be used to give an indication of the gait phase estimation reliability, e.g., the measured cadence of the left foot should be equal to the measured cadence of the right foot and the cadence of the provided stimulation, and the left foot and right foot should be (roughly) in anti-phase.

(299) In the control loop also use can made of the realization that the feet do not move independently from each other but are connected mechanically via the hip and on neural level via the spinal cord.

(300) In particular, inhibitory reflex circuits in the spinal cord modulate neural firing rates (and hence modulate recruitment of motor neurons through EES).

(301) Note that the example control and estimation routines included herein can be used with various system configurations. The control methods and routines disclosed herein may be stored as executable instructions in non-transitory memory and may be carried out by a control system 10 e.g. as a part of the controller 14 in combination with the sensors 12, the programmer 16, the stimulation system 18, the lead 20, and other system hardware. The specific routines described herein may represent one or more of any number of processing strategies such as event-driven, interrupt-driven, multi-tasking, multi-threading, and the like. As such, various actions, operations, and/or functions illustrated may be performed in the sequence illustrated, in parallel, or in some cases omitted. Likewise, the order of processing is not necessarily required to achieve the features and advantages of the example embodiments described herein but is provided for ease of illustration and description. One or more of the illustrated actions, operations and/or functions may be repeatedly performed depending on the particular strategy being used. Further, the described actions, operations and/or functions may graphically represent code to be programmed into non-transitory memory of a computer readable storage medium in the controller 14, where the described actions are carried out by executing the instructions in a control system 10 including the various hardware components.

REFERENCES

(302) 10 control system 12 sensor 12a inertial measurement unit (IMU) 12b pressure sensor 12c sensor network 14 controller 16 programmer 18 implantable pulse generator (IPG) 20 lead 22 training entity 22a exoskeleton 24 electrode module 24a electrode for FES 24b electrode for EES 100 offline workflow 200 online workflow 300 sensor insole di distal end m movement model pr proximal end L location of the patient L1 remote location of the remote trainer T1 P patient S Shoe T trainer/rehabilitation specialist T1 remote trainer/remote rehabilitation specialist CMB custom muscle blocks COM connection, communication line EES epidural electrical stimulation FMB functional muscle block WL wireless link WSN wireless network, connection STP space time programmer TEL connection, telemetry line LVLat left vastus lateralis RVLat right vastus lateralis Lll left iliopsoas Rll right iliopsoas LRF left rectus femoris RRF right rectus femoris LST left semitendinosus RST right semitendinosus LTA left tibialis anterior RTA right tibialis anterior LMG left medial gastrocnemius RMG right medial gastrocnemius LSol left soleus RSol right soleus LFHL left flexor halluces longus RFHL right flexor halluces longus S101 step of offline workflow S102 step of offline workflow S103 step of offline workflow S104 step of offline workflow S105 step of offline workflow S106 step of offline workflow S201 step of online workflow S202 step of online workflow S203 step of online workflow S204 step of online workflow S205 step of online workflow S206 step of online workflow