Abstract: A system applies a feedback force along the first axis in response to a repositioning force applied to a component by a user. A controller determines a target position for the component and varies the feedback force in accordance with a position of the component with respect to the target position wherein the feedback force is different in a first direction away from the target position than in a second direction toward the target position.

Abstract: Implementations described herein provide systems and methods for controlling mobile device movement. In one implementation, a preference trigger is identified, and a preference representation is generated. Path input is obtained, and a plan is generated.

Abstract: A method includes determining a first motion plan and a second motion plan based on inputs and determining a preference for the first motion plan relative to the second motion plan. The method also includes identifying one of the inputs as a sensitive input that causes the preference for the first motion plan over the second motion plan, and presenting, using a display, information that describes the first motion plan. The information includes an explanation indicating the sensitive input as a reason why the first motion plan is preferred over the second motion plan. The method also includes communicating and initiating the preferred motion plan.

Abstract: For manufacturing process control, closed-loop control is provided (18) based on a constrained reinforcement learned network (32). The reinforcement is constrained (22) to account for the manufacturing application. The constraints may be for an amount of change, limits, or other factors reflecting capabilities of the controlled device and/or safety.

Abstract: For manufacturing process control, closed-loop control is provided (18) based on a constrained reinforcement learned network (32). The reinforcement is constrained (22) to account for the manufacturing application. The constraints may be for an amount of change, limits, or other factors reflecting capabilities of the controlled device and/or safety.

Abstract: Systems and methods for automatic generation of robot control policies include a CAD-based simulation engine for simulating CAD-based trajectories for the robot based on cost function parameters, a demonstration module configured to record demonstrative trajectories of the robot, an optimization engine for optimizing a ratio of CAD-based trajectories to demonstrative trajectories based on computation resource limits, a cost learning module for learning cost functions by adjusting the cost function parameters using a minimized divergence between probability distribution of CAD-based trajectories and demonstrative trajectories; and a deep inverse reinforcement learning engine for generating robot control policies based on the learned cost functions.

Abstract: Systems and methods for automatic generation of robot control policies include a CAD-based simulation engine for simulating CAD-based trajectories for the robot based on cost function parameters, a demonstration module configured to record demonstrative trajectories of the robot, an optimization engine for optimizing a ratio of CAD-based trajectories to demonstrative trajectories based on computation resource limits, a cost learning module for learning cost functions by adjusting the cost function parameters using a minimized divergence between probability distribution of CAD-based trajectories and demonstrative trajectories; and a deep inverse reinforcement learning engine for generating robot control policies based on the learned cost functions.