Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Corporation

Daniel Nikolaev Nikovski

Diego Romeres

Matthew E Brand

Arvind Raghunathan

Devesh Jha

Michael J Jones

John R Hershey

Bret Harsham

Emil Laftchiev

Jing Zhang

Ajit Gopalakrishnan

Weihong Zhang

Jingyang Xu

Ankur Jain

William Yerazunis

Jonathan Le Roux

Ajay Divakaran

Christopher Laughman

Amir Massoud Farahmand

Dietmar Ebner

Alberto Dalla Libera

Stefano Di Cairano

Regunathan Radhakrishnan

Srikumar Ramalingam

Yiming Zhao

Hiroshi Taguchi

Kadir A Peker

Andrei Kniazev

Dirk Brinkman

Radu Ioan Corcodel

Alan W Esenther

Mamoru Kato

Ruggero Carli

Zhenhua Wang

Yan Zhu

Qing Yan

Fabio Amadio

Amir-massoud Farahmand

Riccardo Antonello

Athanasios Tsiligkaridis

Seiji Shaw

Yanfeng Geng

Wenyu Zhang

Bernard Lidicky

Arvind U Raghunathan

Yinsong Wang

Chuizheng Kong

A robotic controller is provided for generating sequences of movement primitives for sequential tasks of a robot having a manipulator. The controller includes at least one control processor, and a memory circuitry storing a dictionary including the movement primitives, a pretrained learning module, and a graph-search based planning module having instructions stored thereon. The controller to perform steps acquiring a planned task provided by an interface device operated by a user, wherein the planned task is represented by an initial state and a goal state with respect to an object, generating a planning graph by searching a feasible path of the object for the novel task using the graph-search based planning module and selecting movement primitives from the dictionary in the pretrained learning module, wherein the pretrained learning module has been trained based on demonstration tasks, parameterizing the feasible path represented by the movement primitives as dynamic movement primitives (DMPs) using the initial state and goal state, and implementing the parameterized feasible path as a trajectory according to the selected movement primitives using the manipulator of the robot by tracking and following the parameterized for the planned task.

System and method for learning sequences in robotic tasks for generalization to new tasks

A controller for controlling a system that includes a policy to control the system is provided. The controller includes an interface connected to the system, the interface acquires an action state and a measurement state via sensors measuring the system, a memory to store computer-executable program modules including a model learning module and a policy learning module, a processor that performs steps of the program modules. The steps include offline-modeling to generate offline-learning states based on the action state and measurement state using the model learning program, providing the offline states to the policy learning program to generate policy parameters, and updating the policy of the system to operate the system based on the policy parameters.

Method and system for modelling and control partially measurable systems

A controller for controlling an operation of a robot to execute a task is provided. The controller comprises a memory configured to store a set of dynamic movement primitives (DMPs) associated with the task. The set of DMPs comprise a set of at least two dynamical systems: a function representing point attractor dynamics and a forcing function corresponding to a learned demonstration of the task. The controller comprises a processor configured to transform the set of DMPs to a set of constrained DMPs (CDMPs) by determining a perturbation function associated with the forcing function. The perturbation function is associated with a set of operational constraints. The processor is further configured to solve, a non-linear optimization problem for the set of CDMPs based on the set of operational constraints and generate, a control input for controlling the robot for executing the task, based on the solution.

System and method for controlling a robot using constrained dynamic movement primitives

A control system for controlling motion of elevators of a bank of elevators uses a neural network trained for an extended destination prediction of a person based on a partial trajectory of the person to produce a multinomial of the extended destination prediction. The multinomial has at least two dimensions including a first dimension of destinations of the person and a second dimension of time intervals of the person arriving at the destinations of the first dimension. The control system optimizes a schedule of the bank of elevators based on the multinomial, and further controls the bank of elevators according to the schedule.

System and method for controlling motion of a bank of elevators

A computer-implemented method of training an autoencoder to recover missing data is provided. The autoencoder includes an encoder for encoding its inputs into a latent space and a decoder for decoding the encodings from the latent space. The method comprises creating a first training set including a valid data set of multiple dimensions, and training the encoder and the decoder in a first training stage using the first training set to reduce a difference between the valid data set provided to the encoder and a data set decoded by the decoder. The method further comprises creating a second training set comprising an invalid data set, and training the encoder in a second training stage using the second training set to reduce a difference between encodings of valid data instances and encodings of their corresponding invalid data instances.

System and a method for training a neural network having autoencoder architecture to recover missing data

A robot for performing an assembly operation is provided. The robot comprises a processor configured to determine a control law for controlling a plurality of motors of the robot to move a robotic arm according to an original trajectory, execute a self-exploration program to produce training data indicative of a space of the original trajectory, and learn, using the training data, a non-linear compliant control law including a non-linear mapping that maps measurements of a force sensor of the robot to a direction of corrections to the original trajectory defining the control law. The processor transforms the original trajectory according to a new goal pose to produce a transformed trajectory, update the control law according to the transformed trajectory to produce the updated control law, and command the plurality of motors to control the robotic arm according to the updated control law corrected with the compliance control law.

System and method for robotic assembly based on adaptive compliance

A controller for controlling an operation of a system is disclosed. The controller receives an input signal indicative of the operation of the system and rotates a test signal multiple times with different circular shifts to produce different rotations of the test signal forming a matrix data structure with the input signal. The input signal and the test signal are time-series data having values monotonically measured over time. The controller is further configured to apply a sliding three-dimensional (3D) window method to the matrix data structure to produce statistics of the input signal with respect to the rotations of the test signal. The sliding 3D window method iteratively moves window over the matrix data structure to compute a value of the statistics for a segment of the matrix data structure within the window. Furthermore, the controller controls the operation of the system according to the statistics of the input signal.

System control based on time-series data analysis

A control system for controlling an operation of an elevator arranged to service different floors of a building, is disclosed. The control system comprises an input interface configured to receive a measurement of a distance metric to an object located at a service floor in a line-of-sight of a sensor; an output interface configured to cause a display device to display a floor value indicating a destination floor; and a processor configured to compare the received distance metric with a referenced distance metric to estimate a sign of the comparison and a value of the comparison; repeatedly update, until a termination condition is met, the floor value displayed on the display device in a direction of the elevator service indicated by the sign and with a frequency of the update indicated by the value; and cause the elevator to perform the service operation from the service floor to the destination floor.

Method and system for touchless elevator control

A manipulator learning-control apparatus for controlling a manipulating system that includes an interface configured to receive manipulator state signals of the manipulating system and object state signals with respect to an object to be manipulated by the manipulating system in a workspace, wherein the object state signals are detected by at least one object detector, an output interface configured to transmit initial and updated policy programs to the manipulating system, a memory to store computer-executable programs including a data preprocess program, object state history data, manipulator state history data, a Derivative-Free Semi-parametric Gaussian Process (DF-SPGP) kernel learning program, a Derivative-Free Semi-parametric Gaussian Process (DF-SPGP) model learning program, an update-policy program and an initial policy program, and a processor, in connection with the memory, configured to transmit the initial policy program to the manipulating system for initiating a learning process that operates the manipulator system manipulating the object while a preset period of time.

System and design of derivative-free model learning for robotic systems

A system for detecting an anomaly in an execution of an operation of a machine determines a local matrix profile (LMP) of a test signal with respect to the baseline signals. LMP is a time series of values, each LMP value for a time instance is determined for a segment of the test signal based on a minimum distance between the segment of the test signal with corresponding segments of the baseline signals, such that each LMP value is a value of a local dissimilarity of the execution of the operation of the machine with respect to the baseline executions of the operation of the machine. The system determines an accumulation of the LMP values above an LMP threshold and detects an anomaly when the accumulation above an anomaly detection threshold.

System and method for anomaly detection in time-varying system operations

A controller for controlling a heating, ventilating, and air-conditioning (HVAC) system arranged to condition an environment according to HVAC setpoints is provided. The controller is configured to accept target values of thermal states at predetermined locations in the conditioned environment, current values of the thermal states at the predetermined locations in the conditioned environment, and current values of the HVAC setpoints. The controller is further configured to determine, using a neural network, target HVAC setpoints such that a difference in an operation of the HVAC system according to the target HVAC points with respect to the operation of the HVAC system according to the current HVAC setpoints changes thermal states in the predetermined locations in the conditioned environment from the current values of the thermal state to the target values of the thermal state.

System and method for thermal control based on invertible causation relationship

A system for controlling a robotic arm performing insertion of a component along an insertion line accepts measurements of force experienced by the wrist of robotic arm at current position along insertion line and determines probability of value of the force conditioned on the current value of the position according to a probabilistic relationship for the force experienced by the wrist of the robotic arm along the insertion line as a probabilistic function of the positions of the wrist of the robotic arm along the line of insertion. The probabilistic function is learned from measurements of the operation repeatedly performed by one or multiple robotic arms having the configuration of the robotic arm under the control. The system determines a result of anomaly detection based on the probability of the current value of the force and controls the robotic arm based on the result of anomaly detection.

System and method for automatic error recovery in robotic assembly

A system evaluates a plurality of faults in an operation of a machine at a set of future instances of time. The system uses a neural network including a first subnetwork sequentially connected with a sequence of second subnetworks for each of the future instance of time such that an output of one subnetwork is an input to a subsequent subnetwork. The first subnetwork accepts the current time-series data and the current setpoints of operation of the machine. Each of the second subnetworks accepts the output of a preceding subnetwork, an internal state of the preceding subnetwork, and a future setpoint for a corresponding future instance of time. Each of the second subnetworks outputs an individual prediction of each fault of a plurality of faults at the corresponding future instance of time.

Predictive classification of future operations

Systems and methods for determining a model for predictive inference on an operation of a machine. A processor is configured to acquire time series data, the times series data includes training data and test data, the time series data represents an operation of the machine for a period of time, and the training data includes observations labeled with an outcome of the predictive inference. Apply recursive and stable filters for filtering at a training time, at a test time or both, such that a data point in the filtered time series data corresponds to an observation in the time series data that is a function of the corresponding observation and past observations in the time series data preceding the corresponding observation. Determine the model for the predictive inference using the training data, based on filtering the training data with filters to produce filtered time series data, and store in memory.

Methods and systems to predict a state of the machine using time series data of the machine

Systems and methods for determining a pattern in time series data representing an operation of a machine. A memory to store and provide a set of training data examples generated by a sensor of the machine, wherein each training data example represents an operation of the machine for a period of time ending with a failure of the machine. A processor configured to iteratively partition each training data example into a normal region and an abnormal region, determine a predictive pattern absent from the normal regions and present in each abnormal region only once, and determine a length of the abnormal region. Outputting the predictive pattern via an output interface in communication with the processor or storing the predictive pattern in memory, wherein the predictive pattern is a predictive estimate of an impending failure and assists in management of the machine.

Methods and systems for discovery of prognostic subsequences in time series

Growing community of inventors

Brookline, MA, United States of America

Daniel Nikolaev Nikovski