An object handling control device includes one or more processors configured to acquire at least object information and status information representing an initial position and a destination of an object; set, when a grasper grasping the object moves from the initial position to the destination, a first region, a second region, and a third region in accordance with the object information and the status information; and calculate a moving route along which the object is moved from the initial position to the destination with reference to the first region, the second region, and the third region.

A controller controls a motion of an object performing a task for changing a state of the object from a start state to an end state while avoiding collision of the object with an obstacle according to an optimal trajectory determined by solving an optimization problem of the dynamics of the object producing an optimal trajectory for performing the task subject to constraints on a solution of first-order stationary conditions modeling a minimum distance between the convex hull of the object and the convex hull of the obstacle using complementarity constraints.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a motion planning for a robot. One of the methods includes receiving data representing a motion specification for performing a task by a robot in an environment. The motion specification specifies a goal and one or more constraints. An initial motion plan is determined based on the motion specification, where the initial motion plan specifies a trajectory that satisfies the one or more constraints of the motion specification. The initial motion plan is executed by the robot. Sensor data is monitored for detecting a change in the environment. A first updated motion plan is generated for the robot based on the first change in the environment. The first updated motion plan is executed by the robot.

Learning to effectively imitate human teleoperators, even in unseen, dynamic environments is a promising path to greater autonomy, enabling robots to steadily acquire complex skills from supervision. Various motion generation techniques are described herein that are rooted in contraction theory and sum-of-squares programming for learning a dynamical systems control policy in the form of a polynomial vector field from a given set of demonstrations. Notably, this vector field is provably optimal for the problem of minimizing imitation loss while providing certain continuous-time guarantees on the induced imitation behavior. Techniques herein generalize to new initial and goal poses of the robot and can adapt in real time to dynamic obstacles during execution, with convergence to teleoperator behavior within a well-defined safety tube.

A computer-implemented method executed by data processing hardware of a robot causes the data processing hardware to perform operations. The robot includes an articulated arm having an end effector engaged with a constrained object. The operations include receiving a measured task parameter set for the end effector. The measured task parameter set includes position parameters defining a position of the end effector. The operations further include determining, using the measured task parameter set, at least one axis of freedom and at least one constrained axis for the end effector within a workspace. The operations also include assigning a first impedance value to the end effector along the at least one axis of freedom and assigning a second impedance value to the end effector along the at least one constrained axis. The operations include instructing the articulated arm to move the end effector along the at least one axis of freedom.

Methods and systems are provided for high-speed constrained motion planning. In one embodiment, a method includes computing, with a neural network trained on trajectories generated by a non-convex optimizer, a trajectory from one or more initial states of an autonomous system to one or more final states of the autonomous system, updating, with the non-convex optimizer, the trajectory according to kinematic limits and dynamic limits of the autonomous system to obtain a final trajectory, and automatically controlling the autonomous system from an initial state of the one or more initial states to a final state of the one or more final states according to the final trajectory. In this way, efficient and smooth trajectories can be rapidly computed for effective real-time control while accounting for obstacles and physical constraints of an autonomous system.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a robot along a goal path. An initial Cartesian path is generated based on a goal path on a workpiece. Dynamic properties of the robot while the robot traverses an initial joint-space trajectory having an initial velocity profile are obtained. An adjusted velocity profile over the Cartesian path is generated based on the obtained dynamic properties. A trajectory is generated by combining the initial Cartesian path and the adjusted velocity profile.

Systems, methods, devices, and other techniques are described for planning motions of one or more robots to perform at least one specified task. In some implementations, a task to execute with a robotic system using a tool is identified. A partially constrained pose is identified for the tool that is to apply during execution of the task. A set of possible constraints for the unconstrained pose parameter are selected for each unconstrained pose parameter. The sets of possible constraints are evaluated for the unconstrained pose parameters with respect to one or more task execution criteria. A nominal pose is determined for the tool based on a result of evaluating the sets of possible constraints for the unconstrained pose parameters with respect to the one or more task execution criteria. The robotic system is then directed to execute the task, including positioning the tool according to the nominal pose.

Methods and systems are provided for high-speed constrained motion planning. In one embodiment, a method includes computing, with a neural network trained on trajectories generated by a non-convex optimizer, a trajectory from one or more initial states of an autonomous system to one or more final states of the autonomous system, updating, with the non-convex optimizer, the trajectory according to kinematic limits and dynamic limits of the autonomous system to obtain a final trajectory, and automatically controlling the autonomous system from an initial state of the one or more initial states to a final state of the one or more final states according to the final trajectory. In this way, efficient and smooth trajectories can be rapidly computed for effective real-time control while accounting for obstacles and physical constraints of an autonomous system.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a robot along a goal path. An initial Cartesian path is generated based on a goal path on a workpiece. Dynamic properties of the robot while the robot traverses an initial joint-space trajectory having an initial velocity profile are obtained. An adjusted velocity profile over the Cartesian path is generated based on the obtained dynamic properties. A trajectory is generated by combining the initial Cartesian path and the adjusted velocity profile.