Autonomous operations, such as robotic grasping and manipulation, in unknown or dynamic environments present various technical challenges. For example, three-dimensional (3D) reconstruction of a given object often focuses on the geometry of the object without considering how the 3D model of the object is used in solving or performing a robot operation task. As described herein, in accordance with various embodiments, models are generated of objects and/or physical environments based on tasks that autonomous machines perform with the objects or within the physical environments. Thus, in some cases, a given object or environment may be modeled differently depending on the task that is performed using the model. Further, portions of an object or environment may be modeled with varying resolutions depending on the task associated with the model.

A machine learning method for learning an action of a robot including a hand to pick out a workpiece from a container containing a plurality of the workpieces stacked in bulk and install the workpiece such that the workpiece is in a predetermined installation state includes learning a reverse-order action of removing, by the hand, the workpiece in the predetermined installation state after completion of installation, and learning an installation order of the workpiece based on a learning result of the reverse-order action of removing the workpiece.

A multi-armed robotic translation device includes a robotic body that includes a base section and a cover section attached to the base section. A plurality of tentacles is attached to the robotic body. The plurality of tentacles are configured to apply a shear force on the target object to grip the target object using an adhesive force, each tentacle including at least one shape memory alloy wire configured to move the tentacle. A control system is positioned in the robotic body and is configured to provide power and/or control signals to the tentacles.

A method for picking up an object by means of a robotic device. The method includes obtaining at least one depth image of the object; determining, for each of a plurality of points of the object, the value of a measure of the scattering of surface normal vectors in an area around the point of the object; supplying the determined values to a neural network configured to output, in response to an input containing measured scattering values, an indication of object locations for pick-up; determining a location of the object for pick-up from an output which the neural network outputs in response to the supply of the determined values; and controlling the robotic device to pick up the object at the determined location.

A mobile robotic arm configured to provide on-demand assistance is disclosed. In an example, a robotic system includes a platform, at least two wheels connected to the platform and driven by respective motors, a robotic arm having a base that is connected to the platform, an end-effector connected to the robotic arm at an end opposite the base, and a processor communicatively coupled to the respective motors, the robotic arm, and the end-effector. The processor is configured to receive a command or determine that an item has fallen on a floor, locate the item on the floor, determine a distance and a heading to the item, cause the respective motors to move the platform to the item within range of the robotic arm, cause the robotic arm to grasp the item with the end-effector, and cause the robotic arm to provide the item to a user.

A robot that performs work including gripping an object and moving the object is controlled with high accuracy. A computer for controlling the robot that performs the work including gripping the object and moving the object stores trajectory information, acquires operating state information including a value indicating an operating state of the robot during the work and work state information including a value for grasping a state of the object gripped by the robot, generates estimated work state information including a value for grasping a future state of the object gripped by the robot based on the trajectory information, the operating state information, and the work state information, and generates control information for controlling the robot based on the trajectory information, the operating state information, the work state information, and the estimated work state information.

A method and system are herein disclosed wherein a robot handles objects that are large, unwieldy, highly-deformable, or otherwise difficult to contain and carry. The robot is operated to navigate an environment and detect and classify objects using a sensing system. The robot determines the type, size and location of objects and classifies the objects based on detected attributes. Grabber pad arms and grabber pads move other objects out of the way and move the target object onto the shovel to be carried. The robot maneuvers objects into and out of a containment area comprising the shovel and grabber pad arms following a process optimized for the type of object to be transported. Large, unwieldy, highly deformable, or otherwise difficult to maneuver objects may be managed by the method disclosed herein.

One or more embodiments of the present disclosure relate generally to the field of robotic grasping systems, and in particular to an active robotic manipulator that includes a passive grasping component so that the robotic manipulator can grasp a wide variety of objects and simultaneously provide soft grasping features which reduce the risk of damage to objects.

A device that dispenses spacer material is disclosed. The device may be implemented in connection with a robotic palletization/depalletization system. The device may include a mounting hardware configured to mount the device on or adjacent to an end effector of a robotic arm, a communication interface configured to receive a control signal, and an actuator configured to dispense a quantity of spacer material from a supply of spacer material in response to the control signal.

A system and method for autonomously defining regions of interest for a container are provided. The system comprises a platform for supporting the container, a detector for capturing feature data of the container while on the platform, and a computer system. The computer system is in communication with the detector and platform. The computer system is programmed to locate features of the container from the captured feature data, and define the regions of interest for the container based on the located features.