Abstract: A method for executing a process, in particular using at least one robot, includes executing a run-through of the process, detecting a value of a first process variable, and detecting an assessment of this executed process run-through. Assessment learning steps are then repeated multiple times, wherein run-throughs of the process using varied process controls are executed and additional assessments are detected. A first quality factor model of the process, which model determines a quality factor for the process on the basis on the first process variable, is machine-learned based on the detected assessments and values of the first process variable. The method further includes repeating process control optimization steps multiple times.

Abstract: The robot control system includes a first control device and a second control device network-connected to the first control device to control a robot. The first control device includes a selection unit configured to enable any one of a plurality of sources that provide information about generation of a command instructing behavior of the robot, and a first communication unit configured to transmit a command generated according to the information from the enabled source in the plurality of sources to the second control device. The second control device includes a second communication unit configured to receive the command transmitted from the first control device, and a command value generation unit configured to sequentially generate a command value for driving each axis of the robot so as to provide the behavior instructed by the command from the first control device.

Abstract: A sensor cleaning mechanism is provided herein. At least one sensor is configured to observe a condition associated with a vehicle. A housing is configured to be mounted on the vehicle. The housing includes a window surface configured to be disposed substantially within a field of view of the at least one sensor. A fluid providing mechanism is configured to provide fluid to the window surface. An actuating mechanism is configured to rotate the housing about the at least one sensor at a first speed, thereby causing at least a portion of the fluid to be expelled from the window surface. The actuating mechanism also can be configured to change a speed of rotation of the housing to a second speed, which is greater than zero, in response to a determination that the window surface is substantially clear of the fluid.

Abstract: A robot hand includes a motor, claws configured to grip a workpiece in accordance with rotation of the motor, an encoder configured to detect a rotational position of the motor, and a control device configured to control a torque of the motor such that the claws grip the workpiece in accordance with the rotational position.

Abstract: This disclosure describes systems, methods, and devices related to robotic drive control device. A robotic device may receive an indication associated with pressing an actuator on a handheld device, wherein the handheld device controls a movement of an end effector of the robotic device. The robotic device may record a home location associated with where the actuator was pressed in space. The robotic device may determine an orientation of the handheld device. The robotic device may detect a movement of the handheld device from the home location to a second location in space. The robotic device may cause the end effector of the robot to move in the same orientation as the handheld device from a stationary position that is associated with the home location while continuing to move the end effector even when the handheld device stops moving at the second location.

Abstract: A method for controlling a robot is provided. The method includes the steps of: determining a target robot to travel to a first loading station among a plurality of robots, on the basis of information on a location of the first loading station and a task situation of each of the plurality of robots, when a first transport target object is placed at the first loading station; and determining a travel route of the target robot with reference to information on the location of the first loading station and a location of a first unloading station associated with the first transport target object.

Abstract: A robotic system for inspecting a part comprises a robot comprising an articulating arm and an end effector, coupled to the articulating arm. The robotic system further includes three or more proximity sensors on the end effector and spaced apart from each other. Each of the proximity sensors is configured to detect a measured distance from the proximity sensor to a surface, such that the end effector is displaced from the surface. The robotic system includes a controller configured to receive measured distances from the proximity sensors. The controller is also configured to orient the end effector to a predetermined orientation based on the measured distances. The controller is further configured to calculate an average of the measured distances. Additionally, the controller is configured to move the end effector to a predetermined operating distance from the surface based on the average of the measured distance.

Abstract: A method and system for motion planning for robots with a redundant degree of freedom. The technique computes a collision avoidance motion plan for a robot with a redundant degree of freedom, without artificially constraining the extra degree of freedom. The motion planning is formulated as a quadratic programming optimization calculation having a multi-component objective function and a collision avoidance constraint function. The formulation is efficient enough to compute the motion plan in real time at every robot control cycle. The collision avoidance constraint ensures clearance of all parts of the robot from both static and dynamic obstacles. Objective function terms include minimizing path deviation, joint velocity regularization and robot configuration or pose regularization. Weighting factors on the terms of the objective function are changeable for each control cycle calculation based on obstacle proximity conditions at the time.

Abstract: A method includes defining a virtual object and defining a first point and a second point associated with a virtual representation of a surgical tool. Movement of the virtual representation of the surgical tool corresponds to movement of the surgical tool in real space. The method includes controlling a robotic device coupled to the surgical tool to constrain the first point to the virtual object, determining that the first point is at a threshold position along the virtual object, and controlling the robotic device to guide the second point to the virtual object.

Abstract: A method of avoiding collision between mechanical equipment (10) and obstacles, and a device and controller for this, by detecting whether an external conductor is approaching the device (10); when detecting that the external conductor is approaching the mechanical equipment (10), generating an electrical signal representing a distance between the external conductor and the housing of the mechanical equipment (10) or a change of the distance between the external conductor and the housing of the mechanical equipment (10); controlling the mechanical equipment (10) based on electrical signal so as to avoid the mechanical equipment (10) from collision with the external conductor or to reduce a strength of the collision.

Abstract: Approaches to managing navigation of autonomous vehicles through minor-major intersections are disclosed. A minor-major intersection is detected. Shadow tracks are generated for occlusions associated with the minor-major intersection. A maneuver evaluation is performed based on induced kinematic discomfort and post-encroachment time. Preliminary lateral and longitudinal planning is performed based on shadow tracks, induced kinematic discomfort and post-encroachment time to generate one or more proposed trajectories. Final trajectory generation is performed by refining at least one of the one or more proposed trajectories to generate the final trajectory. The autonomous vehicle performs a selected maneuver corresponding to the final trajectory within the minor-major intersection.

Abstract: To generate an easy-to-understand program for a robot in a simple way. A robot programming device performs programming using an operation unit block. The robot programming device includes a display control unit that displays a programming region and an advanced setting region on a display unit. The programming region is a region for programming for running the robot by setting an operation unit block defined for each operation unit of the robot. The advanced setting region is a region for making setting relating to the operation unit block.

Abstract: One embodiment comprises a method of operating a robotic system. The method comprises defining a Tool Center Point (TCP) for an end effector of the robotic system, providing a primary control plan that defines a tool path for the end effector, where the tool path has a plurality of pre-defined TCP positions. The method further comprises providing a secondary control plan that defines operation of the end effector at the plurality of pre-defined TCP positions, and determining a deviation between a pre-defined TCP position of the end effector and an actual TCP position of the end effector during implementation of the primary control plan by the robotic system. The method further comprises modifying the secondary control plan for the end effector based on the deviation during the implementation of the primary control plan by the robotic system.

Abstract: A center device includes a database storing a plurality of information items regarding a vehicle. The center device identifies a vehicle state by integrating the plurality of information items stored in the database. The center device generates visualization information to be displayed by a display device from an identification result of the vehicle state. The center device transmits the visualization information to the display device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a robot to perform a custom real-time action that uses a callback function. One of the methods comprises receiving a definition of a custom real-time control function that specifies a custom callback function, an action, and a custom reaction that references the custom callback function; providing a command to initiate the action; repeatedly executing, by the control layer of the real-time robotics control framework, the custom real-time control function at each tick of a real-time robotics system driving one or more physical robots, including: obtaining current values of one or more state variables, evaluating the custom reaction specified by the custom real-time control function according to the current values of the one or more state variables, and whenever the one or more conditions of the custom reaction are satisfied, invoking the custom callback function.

Abstract: Techniques and apparatus describe a robotic workcell for performing a robotic stowing operation. The robotic workcell includes a mechanism system, which includes a first robotic gantry, a second robotic gantry, and a controller. The first robotic gantry includes a first mount and a robotic end effector(s) attached to the first mount. The second robotic gantry includes a second mount and at least one end effector attached to the second mount. The controller controls movement of the first mount, the second mount, and the robotic end effector(s), based in part on an analysis of an environment with one or more perception sensors.

Abstract: Embodiments of a learning-based excavation planning method are disclosed for excavating rigid objects in clutter, which is challenging due to high variance of geometric and physical properties of objects, and large resistive force during the excavation. A convolutional neural network is utilized to predict a probability of excavation success. Embodiments of a sampling-based optimization method are disclosed for planning high-quality excavation trajectories by leveraging the learned prediction model. To reduce simulation-to-real gap for excavation learning, voxel-based representations of an excavation scene are used. Excavation experiments were performed in both simulation and real world to evaluate the learning-based excavation planners. Experimental results show that embodiments of the disclosed method may plan high-quality excavations for rigid objects in clutter and outperform baseline methods by large margins.

Abstract: To solve the above problem, a control apparatus, a program, and a system that are capable of effectively providing picking information are provided. According to an embodiment, a control apparatus includes an image interface, a communication unit, and a processor. The image interface obtains an instruction image indicating information of articles to be picked. The communication unit transmits and receives data to and from a robot system that picks the articles. The processor generates picking information of the articles to be picked from the instruction image, and transmits the picking information to the robot system via the communication unit.

Abstract: Systems and methods for modeling electric vehicle towing are disclosed herein. An example method includes determining that a trailer is connected to a vehicle, generating a surface mapping of the trailer based on output of a sensor assembly of the vehicle, predicting a drag coefficient of the trailer based on the surface mapping, estimating a drag force based on the drag coefficient and the surface mapping, calculating an estimated range for the vehicle based on the drag force, and displaying the estimated range on a human machine interface of the vehicle.

Abstract: An example method includes determining objects and actions associated with the objects for completing a task to be executed by a robotic system, where each action is associated with trajectory. The method further includes determining a pose for each person in an environment associated with the robotic system, predicting a trajectory for each person based on the determined pose associated with the respective person and the actions and trajectories associated with the actions, and adjusting trajectories for one or more of the actions to be performed by the robotic system based on the predicted trajectories for each person.