A robot stability control method includes: obtaining a desired zero moment point (ZMP) and a fed-back actual ZMP of a robot at a current moment; based on a ZMP tracking control model, the desired ZMP and the actual ZMP, calculating a desired value of a motion state of a center of mass of the robot at the current moment, wherein the desired value of the motion state of the center of mass comprises a correction amount of the position of the center of mass; based on a spring-mass-damping-acceleration model and the desired value of the motion state of the center of mass, calculating a lead control input amount for the correction amount of the position of the center of mass; and controlling motion of the robot according to the lead control input amount and a planned value of the position of the center of mass at the current moment.

One embodiment of the present invention sets forth a technique for generating simulated training data for a physical process. The technique includes receiving, as input to at least one machine learning model, a first simulated image of a first object, wherein the at least one machine learning model includes mappings between simulated images generated from models of physical objects and real-world images of the physical objects. The technique also includes performing, by the at least one machine learning model, one or more operations on the first simulated image to generate a first augmented image of the first object. The technique further includes transmitting the first augmented image to a training pipeline for an additional machine learning model that controls a behavior of the physical process.

This disclosure discloses various technical features for creating robotic humanoid movements, actions, and interactions with tools and the instrumented environment by automatically building movements for the humanoid; actions and behaviors of the humanoid based on a set of computer-encoded robotic movement and action primitives. The primitives are defined by motions/actions of articulated degrees of freedom that range in complexity from simple to complex, and which can be combined in any form in serial/parallel fashion. These motion-primitives are termed to be minimanipulations and each has a clear time-indexed command input-structure and output behavior/performance profile that is intended to achieve a certain function. Minimanipulations comprise a new way of creating a programmable-by-example platform for robots. The minimanipulation electronic libraries provide a large suite of higher-level sensing-and-execution sequences that are common building blocks for complex tasks, such as cooking, taking care of the infirm, or other tasks performed by robots.

A “Tactile Autonomous Drone” (TAD) (e.g., flying drones, mobile robots, etc.) supplies real-time tactile feedback to users immersed in virtual reality (VR) environments. TADs are not rendered into the VR environment, and are therefore not visible to users immersed in the VR environment. In various implementations, one or more TADs track users as they move through a real-world space while immersed in the VR environment. One or more TADs apply tracking information to autonomously position themselves, or one or more physical surfaces or objects carried by the TADs, in a way that enables physical contact between those surfaces or objects and one or more portions of the user's body. Further, this positioning of surfaces or objects corresponds to some real-time virtual event, virtual object, virtual character, virtual avatar of another user, etc., in the VR environment to provide real-time tactile feedback to users immersed in the VR environment.

A press working simulator according to an aspect of the present disclosure includes: a robot program storage section that stores a robot program that instructs a robot how to move; a press program storage section that stores a press program that instructs a press machine how to move; a profile data setting section that causes the press program storage section to store a press program according to profile data that records what position a die is in at each time point when the press machine is actually moved; a model placing section that places three-dimensional models of a workpiece, the robot, and the press machine in a virtual space; a press movement processing section that causes the three-dimensional model of the press machine to move according to the press program; and a robot movement processing section that causes the three-dimensional model of the robot to move according to the robot program.

A modular robotic device is provided. The modular robotic device includes a robot base and a robotic manipulator connected to the robot base and operable to articulate a tool device connected to an end of the robotic manipulator. The robotic manipulator includes a plurality of modular rigid segments, wherein each of the plurality of modular rigid segments includes a joint portion and each operable to be selectably connected to the robotic manipulator. The plurality of modular rigid segments is interchangeable and operable to be assembled in various combinations.

A nervous system emulator engine includes working computational models of the vertebrate nervous system to generate lifelike animal behavior in a robot. These models include functions representing several anatomical features of the vertebrate nervous system, such as spinal cord, brainstem, basal ganglia, thalamus, and cortex. The emulator engine includes a hierarchy of controllers in which controllers at higher levels accomplish goals by continuously specifying desired goals for lower-level controllers. The lowest levels of the hierarchy reflect spinal cord circuits that control muscle tension and length. Moving up the hierarchy into the brainstem and midbrain/cortex, progressively more abstract perceptual variables are controlled. The nervous system emulator engine may be used to build a robot that generates the majority of animal behavior, including human behavior. The nervous system emulator engine may also be used to build working models of nervous system functions for clinical experimentation.

A robot interference checking motion planning technique using point sets. The technique uses CAD models of robot arms and obstacles and converts the CAD models to 3D point sets. The 3D point set coordinates are updated at each time step based on robot and obstacle motion. The 3D points are then converted to 3D grid space indices indicating space occupied by any point on any part. The 3D grid space indices are converted to 1D indices and the 1D indices are stored as sets per object and per time step. Interference checking is performed by computing an intersection of the 1D index sets for a given time step. Swept volumes are created by computing a union of the 1D index sets across multiple time steps. The 1D indices are converted back to 3D coordinates to define the 3D shapes of the swept volumes and the 3D locations of any interferences.

A controller for robot arms and the like having mechanical singularities identities paths near the singularities and modifies those paths to avoid excessive joint movement according to a minimization of tool orientation deviation to produce alternative paths that minimize changes in the tool orientation such as can affect application such as welding, sealant application, coating and the like.

A transfer source operation information acquisition unit acquires a plurality of pieces of action information about the transfer source robot; a transfer destination operation information acquisition unit acquires a plurality of pieces of first action information about the transfer destination robot; and a correction unit generates a plurality of pieces of second action information about the transfer destination robot by correcting action information about the transfer source robot by a prescribed update formula using the first action information about the transfer destination robot. The number of the pieces of the first action information about the transfer destination robot is smaller than the number of the pieces of the action information about the transfer source robot, and the number of the pieces of the second action information about the transfer destination robot is larger than the number of the pieces of the first action information about the transfer destination robot.