Abstract: An actuator and end effector are controlled according to images from cameras having a surface in their field of view. Vessels (cups, bowls, etc.) and other objects are identified in the images and their configuration is assigned to a finite set of categories by a classifier that does not output a 3D bounding box or determine a 6D pose. For objects assigned to a first subset of categories, grasping parameters for controlling the actuator and end effector are determined using only 2D bounding boxes, such as oriented 2D bounding boxes. For objects not assigned to the first subset, a righting operation may be performed using only 2D bounding boxes. Objects that are still not in the first set may then be grasped by estimating a 3D bounding box and 6D pose.

Abstract: Systems and methods for auto-generating a control and monitoring solution for smart and robotics environments. The traditional systems and methods provide solutions for the smart and robotics environments by manually generating codes but none of them provide for auto-generation of the control and monitoring solutions and the corresponding coordination logics. Embodiments of the present disclosure provide for auto-generating the control and monitoring solution by capturing a set of domain knowledge and information on capabilities of a plurality of devices by an accumulator module (201), auto-generating a controlled coordination logic based upon the set of domain knowledge and the capabilities information by a control logic synthesizer module (202) and auto-generating, by an implementation module (203), the control and monitoring solution for the smart and robotics environments based upon the coordination control logic.

Abstract: A robotic unit for manipulating items and products may receive assistance from a product management system if an exception occurs indicating the robotic unit cannot complete a given task with respect to handling the product. The product management system may be associated with a plurality of different assistance centers and response centers providing different types or levels of assistance. The product management system can classify the exception according to hierarchal tiers to determine the type of assistance required. The product management system can then generate and direct an intervention request to one of the response centers based on the classification. The assistance and response centers may be equipped and staffed to provide particularized assistance to the robotic unit. In an example, the robotic unit may store data and instructions received from the assistance and response center for future implementation.

Abstract: In a robot having a first rotary shaft and a second rotary shaft driven by respective motors and extending in the same direction, the second rotary shaft is rotated while vibrating the first rotary shaft that is holding a load directly or indirectly, thereby rotating the first rotary shaft relative to a load. This enables calculating the gravitational torque of the load applied to the first rotary shaft.

Abstract: A system for controlling wheel brakes in a first vehicle platooning with a second vehicle includes a transceiver in the first vehicle that receives a brake command from the second vehicle to apply a wheel brake in the first vehicle. A controller in the first vehicle generates, responsive to the brake command, a first set of control signals that control delivery of fluid pressure to the wheel brake and implement a braking event. The controller may further detect a wheel slip condition indicative of slip in a wheel of the first vehicle during the braking event and generate, when the condition occurs, a second set of control signals to control delivery of fluid pressure to the wheel brake. The control signals are generated in accordance with braking profiles that differ from braking profiles used by the controller during braking events occurring in the absence of the brake command.

Abstract: An automated guided vehicle control system includes an automated guided vehicle (AGV) transporting parts by moving along a guide line designed on a floor of a factory; and a server displaying a guide line map of the factory on a screen through an AGV path setting UI, setting a transport path of the AGV depending on selection of a node which is present in the guide line and AGV motion information considering a link direction between neighboring nodes included in the transport path and transmitting the set transport path and motion information to the AGV through a wireless relay.

Abstract: A method of controlling a robotic arm in a surgical system comprises manually applying a force to a body of the robotic arm. Force information is received from a gesture force sensor on the robotic arm and a controller determines, using the force information, whether the force is a gesture force input. If the force is determined to be a gesture force input, the controller initiates a predetermined system function. The predetermined system function may be a change in operational state, movement between operational modes, or a movement from a first configuration of the arm's joints to a second, predetermined, configuration of the arms joints.

Abstract: A detection system includes a first detection apparatus that detects an object that is being moved, within a predetermined detection region, a number of times, a work-data creation device that creates, every time the first detection apparatus detects the object, work data having a first data element that indicates at least a position of the object obtained by the first detection apparatus and a second data element that includes at least an index related to the object and obtained at the time of the detection, and a work-data storage unit that stores the work data created by the work-data creation means. The work-data storage unit selects, as the work data that should be stored, one of the work data that is newly created for the object and the work data for the object that has been stored by the work-data storage unit, on the basis of the index.

Abstract: Systems and a method are provided for programming a cobot for a plurality of cells of an industrial environment. A physical cobot is provided within a lab cell comprising physical lab objects. A virtual simulation system receives information inputs on a virtual cobot representing the physical cobot, regarding a virtual lab cell comprising virtual lab objects, and on a plurality of virtual industrial cells comprising virtual industrial objects. Inputs are received from the physical cobot's movement during teaching whereby the physical cobot is moved in the lab cell to the desired position(s) while providing, via a user interface, a visualization of the virtual cobot's movement within a meta cell generated by superimposing the plurality of virtual industrial cells with the virtual lab cell, so that collisions with any object are minimized. A robotic program is generated based on the received inputs of the physical cobot's movement.

Abstract: An automation system, a method and an apparatus for suggesting and/or creating an agent in an industrial automation system that includes automation devices having a framework which is formed to execute the agent and which at least partially includes a data source that collects and/or processes data of the automation devices, and includes a data sink, in which data, in particular status data, of the data sources is saved, wherein an agent suggestion component processes data of the data sink into clusters via a cluster analysis, and wherein the agent suggestion component makes the clusters available at an interface such that a model for the agents becomes creatable by an agent generation component based on at least one selection of the clusters such that it becomes possible to suggest and/or create agents in a simpler and more efficient manner.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for evaluating robot learning. In some implementations, one or more computers receive object classification examples from a plurality of robots. Each object classification example includes (i) an embedding that a robot generated using a machine learning model, and (ii) an object classification corresponding to the embedding. The object classification examples are evaluated based on a similarity of the received embeddings with respect to other embeddings. A subset of the object classification examples is selected based on the evaluation of the quality of the embeddings. The subset of the object classification examples is distributed to the robots in the plurality of robots.