Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Corporation

Mouhacine Benosman

Rui Ma

Saleh Nabi

Petros T Boufounos

Hassan Mansour

Scott Bortoff

Anthony Vetro

Dong Tian

Seiji Watanabe

Jeroen Van Baar

Stefano Di Cairano

Arvind Raghunathan

Ankush Chakrabarty

Daiki Fukui

Piyush Grover

Alan Sullivan

Devesh Jha

Diego Romeres

Daisuke Nakazawa

Chouaib Kantana

Chun Wei

Boris Kramer

Caglayan Dicle

Richard C Waters

Vijay Shilpiekandula

Daniel Antonio Da Costa Dinis

Radu Ioan Corcodel

Siddarth Jain

Reazul Hasan Russel

Richard Vaccaro

Vahan Huroyan

Orlando Romero

Sanjana VijayShankar

Saviz Mowlavi

Siqi Zhang

Gokhan Atinc

Evangelos Polymeneas

Sufeng Niu

Koushik Manjunatha

Jeff Borggaard

Jorge Poveda

Soyeon Jeong

Yuying Liu

Patrik Kolaric

The present disclosure discloses a system and a method for controlling an operation of a machine including at least one actuator. The method comprises obtaining a time period of an operation of the at least one actuator, collecting an energy level of the at least one actuator, and determining one or more hyperparameters of a time bound function such that a value of the time bound function is greater than or equal to the time period of the operation of the at least one actuator. The method further comprises solving an optimal control problem optimizing a cost function of the operation of the at least one actuator using an adaptive gradient descent method that is initialized with the collected energy level and a constant defined based on the one or more hyperparameters and controlling the at least one actuator based on a solution of the optimal control problem.

System and method for controlling an operation of a machine including at least one actuator

A computer-implemented method using a reinforcement learning trained reduced order estimator (RL-trained ROE) and a closure model is provided for controlling a heating, ventilation, and air conditioning (HVAC) system including actuators. The method uses a processor coupled with a memory storing instructions implementing the method, wherein the instructions, when executed by the processor, carry out at steps of the method, includes acquiring setpoints of the HVAC system from a user input and measurement data from sensors arranged in the HVAC system,

Time-varying reinforcement learning for robust adaptive estimator design with application to HVAC flow control

A system for performing a task according to a reference trajectory is provided. The system includes at least one actuator configured to change a state of the system according to a control input, and a memory configured to store a model of dynamics of the system including a known part of the dynamics of the system as a function of the state of the system and the control input to the system and an unknown part of the dynamics of the system as a function of the state of the system, wherein the unknown part of the dynamics of the system is represented by parameters of a probabilistic distribution including a first-order moment and a second-order moment of the probabilistic distribution. The system also includes a control system configured to recursively determine and submit the control input to the actuator to change the state of the system.

System for performing a task according to a reference trajectory

A system for parameter tuning for robotic manipulators is provided. The system includes an interface configured to receive a task specification, a plurality of physical parameters, and a plurality of control parameters, wherein the interface is configured to communicate with a real-world robot via a robot controller. The system further includes a memory to store computer-executable programs including a robot simulation module, a robot controller, and an auto-tuning module a processor, in connection with the memory. In this case, the processor is configured to acquire, in communication with the real-world robot, state values of the real-world robot, state values of the robot simulation module, simultaneously update, by use of a predetermined optimization algorithm with the auto-tuning module, an estimate of one or more of the physical, and said control parameters, and store the updated parameters.

Simulation-in-the-loop tuning of robot parameters for system modeling and control

An auto-tuning controller for improving a performance of a power amplifier system is provided. The controller includes an interface including input terminals and output terminals, the interface being configured to acquire input signal conditions of power amplifiers (PAs), a training circuit including a processor and a memory running and storing a Digital Doherty amplifier (DDA) controller (module), a DPD controller (module) and a DDA-DPD neural network (NN). The training circuit is configured to perform sampling the input signal conditions, and selecting a DPD model from a set of polynomial models for the DPD controller and a set of DDA optimization variables for the DDA controller, using optimized DPD model and DDA coefficients, wherein the optimized DPD model and DDA coefficients are provided by performing an offline optimization for the DPD model and DDA coefficients based on a predetermined optimization method, collecting the optimized DPD coefficients and optimized DDA optimization variables, generating online-DDA optimal coefficients and DPD optimal coefficients using a trained DDA-DPD NN, and updating the generated optimal DDA and DPD coefficients via the output terminals of the interface.

Deep learning-based online adaptation of digital pre-distortion and power amplifier systems

An apparatus for controlling an operation of a system is provided. The apparatus comprises an input interface configured to receive a state trajectory of the system, and a memory configured to store a model of dynamics of the system including a combination of at least one differential equation and a closure model. The apparatus further comprises a processor configured to update the closure model using reinforcement learning (RL) having a value function reducing a difference between a shape of the received state trajectory and a shape of state trajectory estimated using the model with the updated closure model, and determine a control command based on the model with the updated closure model. Further, the apparatus comprises an output interface configured to transmit the control command to an actuator of the system to control the operation of the system.

Apparatus and method for control with data-driven model adaptation

An autotuning controller is provided for improving power efficiency and linearity of digital power amplifiers (DPAs). The controller includes an interface including input and output terminals connected to the DPAs, the interface being configured to acquire input signals and output signals, a digital pre-distortion (DPD)-DPA adaptive controller including a processor and a memory running and storing a DPD algorithm, an efficiency enhancement method and a learning cost function. The DPD adaptive controller is configured to perform steps of computing DPD coefficients to define a learning cost function based on a DPD model by use of a data-driven optimization method, wherein the leaning cost function includes both variables of a DDA performance and a DPD performance, updating the learning cost function based on the DPD performance, optimizing the updated learning cost function by solving the updated learning cost function with respect to the variables of the DDA performance, and providing optimal parameters for DPA and DPD via the interface.

Interactive online adaptation for digital pre-distortion and power amplifier system auto-tuning

A system a method for controlling an operation of HVAC system is provided. The system comprises at least one processor; and memory having instructions stored thereon that, when executed by the at least one processor, cause the system to receive data indicative of the operation of the HVAC system and optimize a cost function to reduce a difference between a full thermal state of the conditioned environment simulated from the received data based on a physical model of airflow including a partial differential equation (PDE) and a thermal state of the conditioned environment reconstructed by an observer using a reduced order model (ROM) of airflow including an ordinary differential equation (ODE) from values of the full thermal state at a set of locations, wherein optimization of the cost function is a multivariable optimization of a structure of the observer and a structure of the ODE.

Controlling thermal state of conditioned environment based on multivariable optimization

A computer-implemented method is provided. The computer-implemented includes a data-driven model and a robust closure model stored in a memory by using a processor for controlling a system. The computer-implemented method includes steps of acquiring sensor signals from at least one sensor of the system via an interface, computing a state of the system based on the sensor signals, determining a gain of the robust closure model based on the state of the system, reproducing a state of the system based on the determined gain, estimating a physics-based model of the system by combining the data-driven model and the robust closure model, and generating control commands by mapping the state of the system using the estimated physics-based model.

Robust adaptive dynamic mode decomposition for modeling, prediction, and control of high dimensional physical systems

A controller for controlling a system having uncertainties in its dynamics subject to constraints on an operation of the system is provided. The controller is configured to acquire historical data of the operation of the system, and determine, for the system in a current state, a current control action transitioning a state of the system from the current state to a next state. The current control action is determined according to a robust and constraint Markov decision process (RCMDP) that uses the historical data to optimize a performance cost of the operation of the system subject to an optimization of a safety cost enforcing the constraints on the operation, wherein a state transition for each of state and action pairs in the performance cost and the safety cost is represented by a plurality of state transitions capturing the uncertainties of the dynamics of the system.

Apparatus and method for controlling a system having uncertainties in its dynamics

A controller for controlling a system is provided. The controller performs measuring variables via an interface to generate a vector of variables, providing a cost function, with respect to the system, based on the vector variables using weighting factors, wherein the vector variables are represented by a time-step, computing first-derivative of the cost function at an initial time-step, obtaining a convergence time from the first-derivative of the cost function, computing second derivative of the cost function and generating an optimization differential equation based on the first and second derivatives of the cost function, proceeding, starting with the initial time-step, to obtain a value of the optimization differential equation by solving the optimization differential equation, in an iteration manner, with a predetermined time step being multiplied with the value of the solved differential equation to obtain next vector variables corresponding to a next iteration time-step, until the time-step reaches the convergence time, and outputting optimal values of the vector of variables and the cost function.

System for continuous-time optimization with pre-defined finite-time convergence

A Digital Power-Amplifier (DPA) system includes a power amplifier (PA) circuit having control inputs and an output for generating output signals, and an adaptive control circuit that comprises an input interface, an output interface, a memory storing an adaptive control algorithm and a processor performing instructions based on the adaptive control algorithm in connection with the memory, wherein the input interface receives input-state signals and output signals of the DPA circuit, wherein the adaptive control algorithm determines, in response to the input-state signals and the output signals, control parameters of control signals transmitted to the control inputs from the output interface for controlling operations of the DPA circuit.

Power amplifier system and transfer learning-based autotuning optimization method thereof

A vehicle control system for driving a vehicle toward a source while avoiding an obstacle includes a first sensor to measure a first intensity of a source signal from the source, a second sensor to detect an obstacle and a second vehicle. The system includes an interface to receive data of a second intensity of the source signal measured by the second vehicle and transmit the data of the first and second intensities via a wireless channel, a memory to store the data of the first and second intensities, an autonomous program, a leader algorithm and a follower algorithm for autonomously driving the vehicle, a processor to select and perform one of the leader algorithm and the follower algorithm and generate control signals, and a machinery control circuit to drive a machinery of the vehicle according the control signals.

Robust source seeking and formation learning-based controller

A system for controlling an operation of an air-conditioning system generating airflow in a conditioned environment, includes a set of sensors to produce measurements of the airflow in a set of points in the conditioned environment, a memory to store a model of the airflow dynamics including a combination of a first term transitioning a previous state of the airflow to a current state of the airflow and a second term assisting the transitioning, an observer to estimate the current state of the airflow in the conditioned environment by transitioning the previous state of the airflow forward in time according to the model of airflow dynamics to reduce the observation error in the current state of the airflow, and a controller to control the air-conditioning system based on the current state of the airflow. The first term in the model includes a projection of a physical model of the airflow on a finite-dimensional space. The physical model of the airflow includes physical parameters of the conditioned environment and the projection preserves the physical parameters of the conditioned environment in the first term. The second term includes a function of the range of the bounded uncertainty of the physical parameter, a negative gain, and an observation error between the measurements of the airflow in the set of points and estimations of the airflow in the set of points according to the model of the airflow.

System and method for controlling operations of air-conditioning system

Power amplifier system and learning-based autotuning method thereof

Growing community of inventors

Boston, MA, United States of America

Mouhacine Benosman