A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

A method and device for evaluating the performance of an industrial control loop based on full loop reconstruction simulations. The method comprises: performing reconstruction simulation on control modules one by one except a controlled object in the loop, and judging the correctness of the reconstructed modules; establishing a mathematical model of the object, connecting the mathematical model to the reconstructed modules to complete reconstruction of the entire loop, and optimizing the mathematical model of the object to obtain an optimized model of the object; adjusting parameters of the modules according to a control performance index, and performing simulation calculation on the reconstructed loop using the parameters to obtain an ideal value of the reconstructed performance control index for evaluating the performance of the loop. The loop is reconstructed, the influence of the modules, a PID controller, a filter, a piece-wise linear function and a deadband, on the performance is evaluated.

A control parameter which causes a servo motor to perform an operation with higher accuracy depending on a purpose and a situation is determined. A control device (10) includes a data evaluation unit (131), a parameter determination unit (132), and an operation data acquisition unit (133). The operation data acquisition unit (133) acquires operation data including a speed or a torque of a servo motor (900). The data evaluation unit (131) calculates an evaluation value by using normative data corresponding to a target of the operation data and the operation data. The parameter determination unit (132) determines a control parameter applied to a servo driver (90) which controls operations of the servo motor (900) by using the evaluation value.

Methods and systems for controlling a physical system (plant) are disclosed. The plant is modeled as a linear, finite-dimensional system having a state vector, a control input vector, a plant output vector, and a disturbance vector comprising disturbances having known basis functions and unknown amplitudes. An adaptive control law is used with separate adaptive gains for an error vector associated with the plant output vector, and the disturbance vector, plus a fixed gain for a disturbance estimator. The adaptive control law is operable to adjust the control input vector so as to minimize the error vector. The plant includes modes which are not Almost Strictly Positive Real (ASPR).

A method to identify physical parameters of a mechanical load with integrated reliability indication includes: applying a first control signal to a mechanical device in a control circuit; measuring a first return signal; and using a power density spectrum of the first return signal to stipulate an excitation signal for the mechanical device.

Driving parameters (e.g., speed, heading direction) that an autonomous driving vehicle (ADV) likely utilize as target driving parameters are grouped into a number of ranges and one of the driving parameters in each range is selected as a driving parameter representative or a target driving parameter representing the respective range or segment. For each of the target driving parameters representing the ranges, a particle swarm optimization method is utilized to derive a set of most optimized coefficients for a controller (e.g., speed controller, steering controller) for controlling an ADV. A driving parameter to coefficient (parameter/coefficient) mapping table is generated to map a particular driving parameter representing a range of driving parameter to a set of one or more coefficients of a particular controller. The parameter/coefficient mapping table is utilized at real-time to configure a controller in response to a particular target driving parameter using the corresponding coefficients.

A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

The present invention is notably directed to a computerized method for providing real-time feedback to a user from states of a model physical system, or MPS, via a computerized system comprising one or more processors and a user interface system, or UIS. The method comprises the following steps, each performed via the one or more processors. Configuration inputs are repeatedly received, to modify a configuration of the MPS, said inputs including user inputs received via said UIS. While receiving said configuration inputs: configurations of the MPS are updated based on the configuration inputs received; and a state of the MPS is repeatedly computed, whereby each computed state corresponds to a latest updated configuration that was available before starting to compute said each computed state. While repeatedly computing a state of the MPS: a surrogate function is obtained, upon completion of each computation, which surrogate function approximates a function of said each computed state; and at least one type of feedback is repeatedly provided via the UIS in respect to said user inputs received. Said at least one type of feedback is provided by sampling the configurations being updated and by evaluating a last surrogate function obtained, and/or a function derived from it, according to the sampled configurations, at a frequency compatible with real-time user-interactivity. The present invention is further directed to related computerized systems and computer program products.

An inspection-plan based inspection method includes receiving data characterizing an inspection plan associated with inspection of one or more nodes in an inspection site by an inspection device. A first step of the inspection plan includes a first set of operating parameters of the inspection device associated with the inspection of a first node of the one or more nodes and a first set of constraints associated with one or more inspection criteria at the first node by the inspection device. The method also includes generating a first control signal configured to instruct the inspection device to inspect the first node of the one or more nodes. The first control signal is based on one or more of the first set of operating parameters and a user input. The method further includes receiving data characterizing the inspection measurement of the first node by the inspection device.