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.

A technique allows verification of a robot operation without any cost for an additional robot or for a person entering a monitoring area. A robot control system includes a monitored robot for which a monitoring area is defined and a robot controller that controls the monitored robot in a plurality of modes including a first mode to change an operation of the monitored robot in response to an object detected in the monitoring area being a robot.

One or more computational strategies is used to reduce the complexity of handling detected point clusters appearing at a portal of a monitored workcell. If the other side of the portal is a second, adjacent workcell, the monitoring system for a first workcell predicts when a human in that workcell may pass through the portal to a second workcell and alerts the monitoring system for the second workcell. The prediction may be based on absolute proximity of a human to the portal or movement toward it. Other strategies are employed if the workcells overlap, or if the portal leads to an unmonitored space.

A switchgear or controlgear with unmanned operation and maintenance includes: an equipment safety system that includes a steering and control system for calculating a action radius of a robot system. An acting area in an internal space of the switchgear or controlgear is divided into virtual zones. Each action in each virtual zone is precalculated predictively as a micro simulation in which actual sensor data are considered before an intended action is triggered.

A method for controlling a robot includes the steps of: deciding whether there is a non-permanent object in a vicinity of the robot; if there is a non-permanent object, deciding whether the object qualifies for extended protection or not; and defining a safety zone around the object which the robot must not enter or in which a maximum allowed speed of the robot is less than outside the safety zone. The safety zone extends to a greater distance from the object if the object qualifies for extended protection than if it does not.

A method and computing system comprising identifying one or more candidate objects for selection by a robot. A path to the one or more candidate objects may be determined based upon, at least in part, a robotic environment and at least one robotic constraint. A feasibility of grasping a first candidate object of the one or more candidate objects may be validated. If the feasibility is validated, the robot may be controlled to physically select the first candidate object. If the feasibility is not validated, at least one of a different grasping point of the first candidate object, a second path, or a second candidate object may be selected.

A collision-detection device for a gripper system of a handling device, with at least two gripping jaws arranged on a flange plate, detects collisions between the gripper system and an object. The device includes a safety device configured to lock the collision-detection device to the gripper system and/or dampen the collision-detection device with the gripper system. The safety device is configured to receive from the flange a change in force and/or a change in torque generated by contact between the gripping jaws and the object. The device further includes a sensor configured to detect a change in distance which exceeds a predetermined permissible change in distance between the flange plate and a reference, the change in distance resulting from the at least one of the change in force and the change in torque.

A vehicle assembly system includes a vehicle chassis of a vehicle; at least one object sensor mounted to the vehicle chassis, where the at least one object sensor generates sensor data based on at least one detected object; a vehicle controller mounted to the vehicle chassis and configured to receive the sensor data from the at least one object sensor, where, during assembly, the vehicle controller is configured with production control software that enables the vehicle controller to generate production object data from the sensor data, monitor for a safety event based on the production object data, and generate a safety event signal in response to detecting the safety event; and a safety controller configured to receive the safety event signal from the vehicle controller and alter a movement of a surveilled machine corresponding to the safety event.

A numerical controller uses specifications to control position-controlled axes of a production machine and determines a current group of position setpoint values and groups of position setpoint values expected for a forecast horizon. The numerical controller checks for the risk of a collision between at least one element moved by the position-controlled axes and at least one other element. The numerical controller carries out the same check for the expected groups. If there is no risk of collision, it stores the expected groups in a braking path memory and uses the current group. If there is the risk of a collision, it changes the axes along a path to a standstill defined by the braking path memory and braking is effected along a path which has been previously checked for the risk of a collision and for which no risk of a collision has been detected.

Apparatuses, systems, and techniques provide a policy that can be executed to cause a machine to move. In at least one embodiment, a first policy layer is provided to cause the machine to execute a first motion that causes the machine to accelerate to reach an unbiased state. A second policy layer is provided to cause the machine to execute a second motion without influencing the unbiased state to be reached by machine. The policy can comprise the first and second policy layers.