Various embodiments are directed to operator workstations that improve efficiency of handling operations at an object handling environment. In one aspect, an operator workstation for handling a plurality of objects is provided. The operator workstation includes a workbench platform having a configurable number of sub-platforms upon which objects can be disposed. The operator workstation further includes a plurality of sensors configured to collect sensor data for detection of object presences and object states of objects disposed upon the workbench platform. The operator workstation further includes a plurality of equipment configured to control movement of objects disposed upon the workbench platform. In various embodiments, different subsets of the sensors and equipment are configured for network communication via different network services provided by a wireless network. For instance, network communication may be provided to different sensors and equipment via different network slices of a 5.sup.th generation new radio (5G) cellular network.

There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.

Embodiments of the present disclosure provide a system, method, apparatus and computer-readable medium for teleoperation. An exemplary system includes a robot machine having a machine body, at least one sensor, at least one robot processor, and at least one user processor operable to maintain a user simulation model of the robot machine and the environment surrounding the robot machine, the at least one user processor being remote from the robot machine. The system further includes at least one user interface comprising a haptic user interface operable to receive user commands and to transmit the user commands to the user simulation model, a display operable to display a virtual representation of the user simulation model.

Provided is a primary-and-secondary robot system including: a primary robot whose posture is changed by external force applied by a user; a secondary robot whose posture is controlled to be the same as the posture of the primary robot; and a control unit that is configured to control the primary robot and the secondary robot, the control unit causing the posture of the primary robot to be the same as the posture of the secondary robot, and limiting an acceleration rate of a movement of the primary robot to a limited acceleration rate or lower in causing the posture of the primary robot to be the same as the posture of the secondary robot.

A self-propelled travelling apparatus includes a travelling controller that controls travelling of the self-propelled travelling apparatus; a receiving unit that receives merchandise and a message associated with the merchandise from a user during travelling of the self-propelled travelling apparatus; and a supplying unit that supplies the message to another user in a case where the other user receives the merchandise while the self-propelled travelling apparatus is travelling after receiving the merchandise and the message.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating control instructions for operating a robot. One of the methods includes generating an interactive user interface that illustrates an object to be manipulated by a robot by using an end effector; receiving, within the user interface, first user input data indicating a workcell location; computing a surface normal of a surface in the workcell corresponding to the workcell location; presenting, within the user interface, a graphical representation of the surface normal corresponding to the workcell location; receiving, within the user interface, second user input data selecting the workcell location; and generating pose data for the robot using the computed surface normal and the workcell location.

A robot teleoperation control device includes a first acquisition unit that acquires operator state information of a state of an operator who operates a robot, an intention estimation unit that estimates an intention of the operator to cause the robot to perform a motion on the basis of the operator state information, a second acquisition unit that acquires at least one of geometric information and dynamic information of the object, an operation method determination unit that determines a method of operating the object based on the estimated motion intention of the operator, and a control amount determination unit that determines a method of operating the robot and force during operation from the information acquired by the second acquisition unit and information determined by the operation method determination unit and reflects the result in a control instruction.

Provided are systems and methods for maximizing saturation of two different sets of actors performing different sets of dependent operations at different rates over different but overlapping periods of time in a non-conflicting manner. The systems and methods may include transferring a first set of ordered items from item storage to item cache locations at a first rate during a first period of time, and fulfilling orders at a faster second rate over a later second period of time by picking items from a first set of the item cache locations at the second rate, and by replacing items at a non-overlapping second set of the item cache locations at the first rate. The transferring is commenced before the picking to create a buffer that allows a first set of actors, operating at the first rate, to continually provide the dependencies needed for a second set of actors to operate at the faster second rate without conflict and with each set of actors operating at their respective maximum rates.

A substrate transport device includes an arm, an end effector coupled to the arm, a driver configured to lift the arm so that the end effector receives a substrate, and a controller configured to control an output of the driver to set a lifting speed of the arm. A difference in height between the end effector and the arm is a position difference. A period from when the end effector contacts the substrate until the end effector completes reception of the substrate is a transition period. The controller sets an upper limit value of the lifting speed that decreases an amplitude of one of acceleration or jerk of the position difference in the transition period as compared to before the transition period to an upper limit value of the lifting speed for the transition period.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for avoiding singular configurations of a robot. A singular configuration of the robot is obtained. A location of an end effector of the robot when the robot is in the singular configuration is determined. For each of a plurality of voxels in a workcell, a distance from the voxel to the location of the end effector when the robot is in the singular configuration is computed. A negative potential gradient of the computed distance is computed. Control rules are generated, wherein the control rules, when followed by the robot, offset the trajectory of the robot according to the negative potential gradient.