Mitsubishi Electric Research Laboratories, Inc.

Marcel Menner

Stefano Di Cairano

Karl Berntorp

Philip Orlik

Kieran Parsons

Jianlin Guo

Ankush Chakrabarty

Kyeong-Jin Kim

Alexander Schperberg

Ziyi Ma

Ferdous Pervej

A control system for controlling a legged robot comprises a processor and a memory. The control system initializes, in response to receiving a task, a probabilistic filter with parameters associated with a state of a reference trajectory of the legged robot, wherein the parameters are predetermined for the task and encode the reference trajectory including a combination of different reference trajectories for coordinated motion primitives of different actuators of the legged robot moving the legged robot according to the task, decodes the parameters to generate the reference trajectory, and executes, in response to receiving a feedback signal, the probabilistic filter to iteratively track the state of the reference trajectory satisfying a performance objective with respect to the state of the legged robot to update the parameters.

Task-specific and environment-specific adaptive control of legged robot

A computer-implemented method is provided for training a global machine learning model using a learning server and a set of vehicle agents connected to roadside units (RSUs). It involves selecting agents, associating them with RSUs based on proximity, and transmitting training data and deadlines. Agents train models locally, which are then aggregated through RSUs to refine the global model to desired precision. The method includes steps of selecting vehicle agents from a pool of the vehicle agents connected to the RSUs, associating the selected vehicle agents and the RSUs respectively based on distances from the selected vehicle agents to the RSUs configured to provide measurements of the distances to the learning server, and transmitting a global model, a selected agent set and deadline thresholds in each global training round to the RSUs configured to transmit the global model and training deadlines to the selected vehicle agents.

Communication and computation aware distributed machine learning for vehicular networks

The present disclosure discloses a system and a method for controlling a vehicle in an environment. The method uses a processor coupled to a memory storing a probabilistic map of the environment relating measurements of a magnetic field and time of the measurements of the magnetic field to a probability of locations within the environment. The processor is coupled with stored instructions when executed by the processor carry out steps of the method comprising estimating a probability of the current location in the environment based on a current measurement of a magnetometer at a current timestamp by submitting the current measurement and the current timestamp to the probabilistic map, and controlling an actuator of the vehicle based on a stochastic control employing the probability of the current location.

System and method for controlling a vehicle in an environment

The present disclosure provides a feedback controller and method for controlling an operation of a device at different control steps. The feedback controller comprises at least one processor, and the memory having instructions stored thereon that, when executed by the at least one processor, causes the feedback controller, for a control step, to collect a measurement indicative of a state of the device at the control step, and execute, recursively until a termination condition is met, a probabilistic solver parameterized on a control input to an actuator operating the device to produce a control input for the control step. The feedback controller is further configured to control the actuator operating the device based on the produced control input.

System and method for controlling an operation of a device

A probabilistic feedback controller for controlling an operation of a robotic system using a probabilistic filter subject to a structural constraint on an operation of the robotic system is configured to execute a probabilistic filter estimates a distribution of a current state of the robotic system given a previous state of the robotic system based on a motion model of the robotic system perturbed by stochastic process noise and a measurement model of the robotic system perturbed by stochastic measurement noise having an uncertainty modeled as a time-varying Gaussian process represented as a weighted combination of time-varying basis functions with weights defined by corresponding Gaussian distributions. The probabilistic filter recursively updates both the distribution of the current state of the robotic system and the Gaussian distributions of the weights of the basis functions selected to satisfy the structural constraint indicated by measurements of the state of a robotic system.

Model-based control with uncertain motion model

A vehicle includes an advanced driver-assistance system (ADAS) configured to intervene in an operation of the control system by complementing or overriding the driving input in response to detecting a driving condition dependent on a calibration parameter indicative of a preference of execution of the driving maneuver. The ADAS is calibrated based on a crowd-local distribution function of the calibration parameter indicative of a distribution of the preference of execution of the driving maneuver by other drivers of other vehicles at a specific location or a specific environment in response to detecting that the vehicle approaches the specific location or the specific environment.

Method and system for driving condition-agnostic adaptation of advanced driving assistance systems

A system for controlling an operation of a machine for performing a task is disclosed. The system submits a sequence of control inputs to the machine and receives a feedback signal. The system further determines, at each control step, a current control input for controlling the machine based on the feedback signal including a current measurement of a current state of the system by applying a control policy transforming the current measurement into the current control input based on current values of control parameters in a set of control parameters of a feedback controller. Furthermore, the system may iteratively update a state of the feedback controller defined by the control parameters using a prediction model predicting values of the control parameters and a measurement model updating the predicted values to produce the current values of the control parameters that explain the sequence of measurements according to a performance objective.

System and method for calibrating feedback controllers

Embodiments of the present disclosure disclose a method and a system for controlling a motion of an electric vehicle (EV). The method includes determining a velocity profile moving the EV from an initial velocity over a period of time by minimizing the energy dissipation according to an energy-loss function. The energy-loss function maps values of acceleration and velocity of the EV to energy dissipation of the EV resulting from controlling one or multiple electric motors of the EV to move the EV at corresponding acceleration and velocity values. The velocity profile is a function of time. The method further includes controlling the one or multiple electric motors of the EV to generate a torque for moving the EV according to the velocity profile.

Method and system for controlling motion of an electric vehicle (EV)

Controller of a vehicle uses control functions to transition the current state of the vehicle into a target state. A control function is probabilistic to output a parametric probability distribution over the target state defined by a first moment and at least one higher order moment. The controller submits the current state into at least a subset of control functions consistent with the next driving decision to produce a subset of parametric probability distributions over the target state, combines the subset of parametric probability distributions to produce a joint parametric probability distribution of the target state, and determines the control command based on the first moment and at least one higher order moment of the joint parametric probability distribution of the target state.

Growing community of inventors

Boston, MA, United States of America

Marcel Menner