The present invention discloses a multi-dimensional surface electromyogram signal prosthetic hand control method based on principal component analysis. The method comprises the following steps. Wear an armlet provided with a 24-channel array electromyography sensor to a front arm of a subject, and respectively wear five finger joint attitude sensors at a distal phalanx of a thumb and at middle phalanxes of remaining fingers of the subject. Perform independent bending and stretching training on the five fingers of the subject, and meanwhile, collect data of an array electromyography sensor and data of the finger joint attitude sensors. Decouple the data of the array electromyography sensor by principal component analysis to form a finger motion training set. Perform data fitting on the finger motion training set by a neural network method, and construct a finger continuous motion prediction model. Predict a current bending angle of the finger through the finger continuous motion model.

A system and method for controlling a device, such as a prosthetic limb are provided. A biomimetic controller of the system comprises a signal processor and a musculoskeletal model. The signal processor processes M biological signals received from a residual limb to transform the M biological signals into N activation signals, where M and N are integers and M is less than N. The musculoskeletal model transforms the N activation signals into intended motion signals. A prosthesis controller transforms the intended motion signals into three or more control signals that are outputted from an output port of the prosthesis controller. A controlled device receives the control signals and performs one or more tasks in accordance with the control signals.

An electrode pair is provided including a first electrode and a second electrode. Each of the first electrode and the second electrode have an outer surface, an inner surface, a first end, a second end, and a lead extending outwardly from the first end. The lead has a first width at the first end. The second end of at least one of the first electrode and the second electrode have a recess formed therein having a first terminus and a second terminus. A second width extends between the first terminus and the second terminus of the recess. The recess is defined by a saw-tooth pattern. When the first electrode is positioned on the second electrode, the recess of the at least one of the first electrode is adjacent the lead of the other electrode.

A soft actuator includes an origami structure with an inflatable hollow body formed from at least one of Dyneema fabric or Kevlar fabric, and a plurality of TCPAs formed from at least one of polyethylene terephthalate, spandex, and nylon. The soft actuator also includes a plurality of heating wires disposed on the plurality of TCPAs and a controller configured to selectively heat the plurality of heating wires such that the plurality of TCPAs are selectively actuated by being heated by the plurality of heating wires.

A soft robotic device includes a flexible body having a width, a length and a thickness, wherein the thickness is at least 1 mm, the flexible body having at least one channel disposed within the flexible body, the channel defined by upper, lower and side walls, wherein at least one wall is strain limiting; and a pressurizing inlet in fluid communication with the at least one channel, the at least one channel positioned and arranged such that the wall opposite the strain limiting wall preferentially expands when the soft robotic device is pressurized through the inlet.

A method includes receiving position information and force information, providing control commands to a steering mechanism of a continuum manipulator based on the position information and the force information, updating a control matrix based on the position information and the provided control commands, and providing updated control commands to the steering mechanism based on the updated control matrix. A continuum manipulator includes a body, a steering mechanism configured to steer the body, sensors, and a controller. The sensors include a position sensor to detect a position of the body and a force sensor to detect a force against the body. The controller is configured to receive position information from the position sensor and force information from the force sensor, provide control commands to the steering mechanism based on the position information and the force information, and update a control matrix based on the position information and the provided control commands.

An electro-hydraulic artificial muscle with three-dimensional interactive stacked electrodes includes at least two flexible conductive electrodes wrapped by a flexible insulation material. The flexible conductive electrodes are interactively stacked, immersed in a fluid dielectric and then are wrapped by a flexible sealing layer. Two ends of the flexible conductive electrodes that are three-dimensionally interactively stacked are led out from the flexible sealing layer to be connected with an external power supply. The two ends of the flexible conductive electrodes that are three-dimensionally interactively stacked are connected with the flexible sealing layer. Under the action of an applied electric field, the flexible conductive electrodes wrapped by the flexible insulation material break down the fluid dielectric and approach each other. Simultaneously, the fluid dielectric between the flexible conductive electrodes wrapped by the flexible insulation material is extruded. According to this process, the function of contracting and expanding the flexible sealing layer in a specific direction is achieved.

A tendon-driven robotic gripper is disclosed for performing fingertip and enveloping grasps. One embodiment comprises two fingers, each with two links, and is actuated using a single active tendon. During unobstructed closing, the distal links remain parallel, creating exact fingertip grasps. Conversely, if the proximal links are stopped by contact with an object, the distal links start flexing, creating a stable enveloping grasp. The route of the active tendon and the parameters of the springs providing passive extension forces are optimized in order to achieve this behavior. An additional passive tendon is disclosed that may be used as a constraint preventing the gripper from entering undesirable parts of the joint workspace. A method for optimizing the dimensions of the links in order to achieve enveloping grasps of a large range of objects is disclosed and applied to a set of common household objects.

An exoskeleton apparatus driven by a pneumatic artificial muscle with functions of upper limb assist and rehabilitation training includes an upper limb frame, a shoulder joint mechanism, and an elbow joint mechanism which are driven by utilizing a processing unit, a first angle sensing unit, a second angle sensing unit, a first proportional pressure valve, a pressure sensing unit and a pneumatic muscle device. The exoskeleton apparatus can be independently used as an upper limb exoskeleton assistive device or can be combined to form an upper limb exoskeleton rehabilitation training system to simulate the upper limb movements in daily life through the upper limb frame to assist with the movements of the wearer's upper limbs, accomplishing the rehabilitation training of each upper and lower arm joint and neurological function.

A lockable connector device and system is described. An example lockable connector device includes a first spherical body connected to a first end of a shaft and a plurality of appendages connected to a second end of the shaft. The appendages partially encase a second spherical body and an actuator connected to the appendages, where the actuator is comprised of synthetic muscles that compress to lock the second spherical body.