A robot control method, and associated robot controllers and robots operating with such methods and controllers, providing real-time vibration suppression. The control method involves learning to support real-time, vibration-suppressing control. The method uses state-of-the-art machine learning techniques in conjunction with a differentiable dynamics simulator to yield fast and accurate vibration suppression. Vibration suppression using offline simulation approaches that can be computationally expensive may be used to create training data for the controller, which may be provide by a variety of neural network configurations. In other cases, sensory feedback from sensors onboard the robot being controlled can be used to provide training data to account for wear of the robot's components.

A method and system for autonomous picking or put-away of items, totes, or cases within a logistics facility. The system includes a remote server and at least one manipulation robot. The system may further include at least one transport robot. The remote server is configured to communicate with the various robots to send and receive picking data, and the various robots are configured to autonomously navigate and position themselves within the logistics facility.

Deep machine learning methods and apparatus, some of which are related to determining a grasp outcome prediction for a candidate grasp pose of an end effector of a robot. Some implementations are directed to training and utilization of both a geometry network and a grasp outcome prediction network. The trained geometry network can be utilized to generate, based on two-dimensional or two-and-a-half-dimensional image(s), geometry output(s) that are: geometry-aware, and that represent (e.g., high-dimensionally) three-dimensional features captured by the image(s). In some implementations, the geometry output(s) include at least an encoding that is generated based on a trained encoding neural network trained to generate encodings that represent three-dimensional features (e.g., shape). The trained grasp outcome prediction network can be utilized to generate, based on applying the geometry output(s) and additional data as input(s) to the network, a grasp outcome prediction for a candidate grasp pose.

Provided is a robot control device that makes it possible to perform high-level operations on a robot from an external device. The robot control device for controlling a robot, includes: a digital input/output interface for transmitting/receiving digital data to/from an external device; a program generation unit which generates an action command for the robot in accordance with command identification data included in digital data inputted via the digital input/output interface; and a program execution unit which executes the generated action command.

A robot is provided. The robot includes a camera, a depth sensor, a memory, and a processor configured to perform an interaction with a first user with a highest degree of interest from among a plurality of users present in vicinity of the robot, obtain gazing information of the plurality of users while performing the interaction with the first user, and obtain distance information of the plurality of users, determine an engagement level of the first user for the interaction by using gazing information and distance information of the first user from among the plurality of users, determine a degree of interest of another user by using gazing information and distance information of the first user and the another user from among the plurality of users, end the interaction with first user, and perform an interaction with the another user based on the degree of interest of the another user.

A method of configuring robot fleets with additive manufacturing capabilities includes receiving a request for a robotic fleet to perform a job and determining a job definition data structure based on the request. The job definition data structure defines a set of tasks to be performed in furtherance of the job. The method includes determining a provisioning configuration for each additive manufacturing system based on the task to which the additive manufacturing system is assigned, the set of 3D printing requirements, the printing instructions, and the status of the additive manufacturing system. The method includes provisioning the additive manufacturing system based on the provisioning configuration and a set of additive manufacturing system provisioning rules that are accessible to an intelligence layer to ensure that provisioned systems comply with the provisioning rules. The method includes deploying the robotic fleet based on the robotic fleet configuration data structure to perform the job.

A robot system comprising movable parts, a casing element, a force limiting sensor, a joint position sensor, and one or more processors, wherein the casing element comprises a vibration actuator. Multiple embodiments are introduced for the implementation of the casing element include haptic warning and proximity sensing. Furthermore, means to use the casing element to guide the robot and generate haptic effect by the vibration actuator to assist the user in a human-robot collaboration and/or guiding function are also disclosed.

An electronic apparatus is provided. The electronic apparatus includes a communicator comprising communication circuitry, a memory storing information on an artificial intelligence model, and a processor configured to: obtain a map generated based on sensing data obtained by an external electronic apparatus, simulate driving of the external electronic apparatus on the obtained map based on a plurality of parameter values and obtain driving result data for the plurality of parameter values, train the artificial intelligence model based on the plurality of parameter values and the obtained driving result data and obtain a plurality of parameter values related to driving of the external electronic apparatus, and control the communicator to transmit the plurality of obtained parameter values to the external electronic apparatus.

A system includes a robotic device, a tool rack, a network access point, a message router, and a first tool. The tool rack includes a tool holster that provides for removable coupling of tools to the tool rack and a wireless tag that indicates a wireless network identifier of the tool rack. The network access point generates a wireless network based on the wireless network identifier. The message router communicatively connects, by way of the wireless network, the robotic device to the tools. The first tool is operable by a manipulator of the robotic device and includes an adapter configured to removably couple to the tool holster, a wireless tag reader that scans the wireless tag when the first tool is coupled to the tool holster, and a processor that connects to the wireless network and communicates with the robotic device by way of the message router.

Aspects of the disclosure relate to intelligent RPA bot development. A computing platform may identify user interface field information from one or more applications based on tracking eye movements of the user. The computing platform may identify device events associated with the eye movements of the user. The computing platform may generate a sequence log associating the eye movements of the user with the device events. The computing platform may derive, using a machine learning model, based on the sequence log, a cognitive model of the transaction by the user. The computing platform may generate a workflow for an autonomous bot by identifying and assembling robotic process automation components based on the derived cognitive model of the transaction by the user. The computing platform may send the workflow for the autonomous bot to a user computing device.