Provided is a configuration for generating pseudo sensor data from a plurality of pieces of existing sensor data. This information processing device which generates time-series learning data on the basis of time-series original data acquired from a robot device comprises: a memory that stores at least one extended data generation rule comprising at least one velocity change value, at least one phase change value, at least one position change value, or at least one magnitude change value; and a processor that generates time-series extended data by data expansion of the original data using at least one change value of the extended data generation rule, and outputs time-series learning data including the time-series extended data and the time-series original data.

A display guided robotic navigation and control system comprises a display system including a display surface and a display device configured to display an image including a visual pattern onto the display surface, a robotic system including a mobile robotic device and an optical sensor attached to the mobile robotic device, and a computing system communicatively connected to the display system and the robotic system. Related methods are also disclosed.

Vehicle navigation control systems in autonomous driving rely on accurate predictions of objects within the vicinity of the vehicle to appropriately control the vehicle safely through its surrounding environment. Accordingly this disclosure provides methods and devices which implement mechanisms for obtaining contextual variables of the vehicle's environment for use in determining the accuracy of predictions of objects within the vehicle's environment.

The present disclosure relates generally to the operation of autonomous machinery for performing various tasks at various industrial work sites, and more particularly to the volumetric estimation and dimensional estimation of a pile of material or other object, and the use of multiple sensors for the volumetric estimation and dimensional estimation of a pile of material or other object at such work sites. An application and a framework is disclosed for volumetric estimation and dimensional estimation of a pile of material or other object using at least one sensor, preferably a plurality of sensors, on an autonomous machine (e.g., robotic machines or autonomous vehicles) in various work-site environments applicable to various industries such as, construction, mining, manufacturing, warehousing, logistics, sorting, packaging, agriculture, etc.

This document describes neuromorphic controllers. In one aspect, a method for controlling one or more joints of a robotic arm includes receiving, by neuromorphic controller comprising a spiking neural network (SNN), a target value of a joint control variable for a joint of the robotic arm. The SNN includes two position proprioceptor neurons, two-speed proprioceptor neurons, a presynaptic inhibitory neuron, an extensor motor neuron, and a flexor motor neuron. The neuromorphic controller updates an actual value of the joint control variable for the joint of the robotic arm based on the target value of the joint control variable. The updating includes generating, by one of the two position proprioceptor neurons, the first spikes to one of the extensors motor neurons or the flexor motor neuron based on a difference between the actual value of the joint control variable and the target value of the joint control variable.

An exemplary method and system are disclosed to flexibly and adaptably manufacture and assemble a workpiece by using recordings of a user in machine learning/artificial intelligence algorithms to train a robot for subsequent automated manufacture. Machine learning and artificial intelligence learning can generate libraries of generalized dynamic motion primitives that can be subsequently combined for any type of manufacturing or assembling activity. The exemplary method and system can flexibly generate a model of an existing workpiece as a template or primer workpiece that can then be used in conjunction with the DMP operations to fabricate subsequent workpieces.

Training and/or using a machine learning model for performing robotic tasks is disclosed herein. In many implementations, an environment-conditioned action sequence prediction model is used to determine a set of actions as well as a corresponding particular order for the actions for the robot to perform to complete the task. In many implementations, each action in the set of actions has a corresponding action network used to control the robot in performing the action.

A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

A control apparatus causes a robot device to move a suction head to a predetermined position at which a workpiece is fed and attempt to pick up the workpiece with the suction head at the predetermined position. Upon determining that the suction head has yet to pick up the workpiece, the control apparatus causes the robot device to rotationally move the suction head spirally in a horizontal direction while causing the suction head to perform a suction operation for the workpiece, and estimates a direction in which the workpiece is located with respect to the predetermined direction based on a change in compressed air pressure during the rotational movement of the suction head.

A method includes receiving sensor data representative of surfaces in a physical environment containing an interaction point for a robotic device, and determining, based on the sensor data, a height map of the surfaces in the physical environment. The method also includes determining, by inputting the height map and the interaction point into a pre-trained model, one or more candidate positions for a base of the robotic device to allow a manipulator of the robotic device to reach the interaction point. The method additionally includes determining a collision-free trajectory to be followed by the manipulator to reach the interaction point when the base of the robotic device is positioned at a selected candidate position of the one or more candidate positions and, based on determining the collision-free trajectory, causing the base of the robotic device to move to the selected candidate position within the physical environment.