In an embodiment, a method includes determining a given material to manipulate to achieve a goal state. The goal state can be one or more deformable or granular materials in a particular arrangement. The method further includes, for the given material, determining, a respective outcome for each of a plurality of candidate actions to manipulate the given material. The determining can be performed with a physics-based model, in one embodiment. The method further can include determining a given action of the candidate actions, where the outcome of the given action reaching the goal state is within at least one tolerance. The method further includes, based on a selected action of the given actions, generating a first motion plan for the selected action.

In one aspect, a method for controlling a compliant-controlled robot includes performing a boundary monitoring of the robot and controlling movement of the robot with a return force that is predetermined by control technology. If the robot is already in a blocked area upon activation of the boundary monitoring, then a first return force operates to return the robot from a current position in the blocked area toward a boundary of the blocked area. If the robot arrived at the current position in the blocked area after activation of the boundary monitoring, then a second return force operates to return the robot from the current position toward the boundary. The first return force is at least temporarily less than the second return force.

A computer-implemented method executed by a robotic system for performing a positional search process in an assembly task is presented. The method includes applying forces to a first component to be inserted into a second component, detecting the forces applied to the first component by employing a plurality of force sensors attached to a robotic arm of the robotic system, extracting training samples corresponding to the forces applied to the first component, normalizing time-series data for each of the training samples by applying a variable transformation about a right tilt direction, creating a time-series prediction model of transformed training data, applying the variable transformation with different directions for a test sample, and calculating a matching ratio between the created time-series prediction model and the transformed test sample.

A system for motion control is presented. In one embodiment, a motion control 3D projection system includes a projector; and a projection surface coupled to a robotic arm, where the robotic arm moves the projection surface through a set of spatial coordinates, and a 3D projection from the projector is projected onto a set of coordinates of the projection surface and matches the 3D projection to the set of coordinates of the projection surface as the projection surface moves through the set of spatial coordinates. In additional embodiments, a master control system may integrate additional robotic arms and other devices to create a motion control scene with a master timeline.

The velocity and force of a target is controlled to have a predetermined relationship, independently of changes in the velocity at which the target is driven using a velocity command value and in an external force from the target. A controller controls a control target, driven to generate a predetermined viscous force as a reaction force, by periodically outputting a command value to the control target using a target value calculated from a command pattern for driving the control target and a feedback value from the control target relative to the target value. A correction operation unit obtains a control physical quantity different from the command value, calculates a correction command value based on a relationship between an error of the obtained control physical quantity from its target value and an error of the feedback value from the target value, and outputs the correction command value to the control target.

A method for controlling a mechanical system having a plurality of components interlinked by a plurality of driven joints, the method comprising: measuring torques or forces about or at the driven joints and forming a load signal representing the measured torques or forces; receiving a motion demand signal representing a desired state of the system; implementing an impedance control algorithm in dependence on the motion demand signal and the load signal to form a target signal indicating a target configuration for each of the driven joints; measuring the configuration of each of the driven joints and forming a state signal representing the measured configurations; and forming a set of drive signals for the joints by, for each joint, comparing the target configuration of that joint as indicated by the target signal to the measured configuration of that joint as indicated by the state signal.

A method for controlling a mechanical system having a plurality of components interlinked by a plurality of driven joints, the method comprising: measuring torques or forces about or at the driven joints and forming a load signal representing the measured torques or forces; receiving a motion demand signal representing a desired state of the system; implementing an impedance control algorithm in dependence on the motion demand signal and the load signal to form a target signal indicating a target configuration for each of the driven joints; measuring the configuration of each of the driven joints and forming a state signal representing the measured configurations; and forming a set of drive signals for the joints by, for each joint, comparing the target configuration of that joint as indicated by the target signal to the measured configuration of that joint as indicated by the state signal.

A method for controlling a mechanical system having a plurality of components interlinked by a plurality of driven joints, the method comprising: measuring torques or forces about or at the driven joints and forming a load signal representing the measured torques or forces; receiving a motion demand signal representing a desired state of the system; implementing an impedance control algorithm in dependence on the motion demand signal and the load signal to form a target signal indicating a target configuration for each of the driven joints; measuring the configuration of each of the driven joints and forming a state signal representing the measured configurations; and forming a set of drive signals for the joints by, for each joint, comparing the target configuration of that joint as indicated by the target signal to the measured configuration of that joint as indicated by the state signal.

Embodiments provide functionality to prevent collisions between robots and objects. An example embodiment detects a type and a location of an object based on a camera image of the object, where the image has a reference frame. Motion of the object is then predicted based on at least one of: the detected type of the object, the detected location of the object, and a model of object motion. To continue, a motion plan for the robot is generated that avoids having the robot collide with the object based on the predicted motion of the object and a transformation between the reference frame of the image and a reference frame of the robot. The robot can be controlled to move in accordance with the motion plan or a signal can be generated that controls the robot to operate in accordance with the motion plan.

A rehabilitation system for rehabilitation of a subject including at least one end-effector for interacting with the subject, the end-effector having at least two degrees of freedom of motion, at least one actuator for actuating the at least one end-effector, at least one sensor for measuring at least the position and the speed of the at least one end-effector; at least one sensor for measuring the interaction force between the subject and the end-effector; a memory including at least two initial coefficients and a session including at least one exercise including at least one reference trajectory to be carried out by the subject through actuation of the end effector; and an actuator controlling unit. The memory delivers the initial coefficients and the session, the sensors deliver measurement signals to the controlling unit, and the controlling unit provides a force-controlled feedback based on the initial coefficients.