A robot control device includes: a learned model created through learning work data composed of input and output data, the input data including states of a robot and the surroundings where humans operate the robot to perform a series of works, the output data including human operation corresponding to the case or movement of the robot caused thereby; a control data acquisition section that acquires control data by obtaining output data related to human operation or movement from the model, being presumed in response to and in accordance with the input data; a completion rate acquisition section acquiring a completion rate indicating to which progress level in the series of works the output data corresponds; and a certainty factor acquisition section that acquires a certainty factor indicating a probability of the presumption in a case where the model outputs the output data in response to the input data.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a trajectory of a robot. One of the methods includes receiving a plurality of path points; processing each network input in an input sequence that is derived from the path points using a trajectory generation neural network to generate an output sequence comprising a plurality of network outputs, each network output specifying a respective displacement between two adjacent trajectory points; and generating, based on the output sequence, a predicted trajectory of the robot.

Mitigating the reality gap through optimization of one or more simulated hardware parameters for simulated hardware components of a simulated robot. Implementations generate and store real navigation data instances that are each based on a corresponding episode of locomotion of a real robot. A real navigation data instance can include a sequence of velocity control instances generated to control a real robot during a real episode of locomotion of the real robot, and one or more ground truth values, where each of the ground truth values is a measured value of a corresponding property of the real robot (e.g., pose). The velocity control instances can be applied to a simulated robot, and one or more losses can be generated based on comparing the ground truth value(s) to corresponding simulated value(s) generated from applying the velocity control instances to the simulated robot. The simulated hardware parameters and environmental parameters can be optimized based on the loss(es).

A robot control device includes: a reliability computing unit that is inputted with a feature quantity obtained from a sensor signal indicating a measurement result obtained by an external sensor installed in a main body of a robot or a surrounding environment of the robot, and computes a reliability for the sensor signal on the basis of a temporal change or a spatial change of the feature quantity; a correction command value computing unit that computes a trajectory correction amount for correcting a trajectory of the robot on the basis of the reliability and correction information calculated on the basis of the feature quantity; and a command value generation unit that generates a location command value for the robot on the basis of a predetermined target trajectory of the robot and the trajectory correction amount.

The invention relates to a method for determining optimized program parameters for a robot program, wherein the robot program is used to control a robot having a manipulator, preferably in a robot cell, comprising the steps: creating the robot program by means of a component-based graphical programming system on the basis of user inputs, wherein the robot program is formed from program components which are parameterizable via program parameters, and wherein initial program parameters are generated for the program components of the robot program; providing an interface for selecting one or more critical program components, wherein optimizable program parameters can be defined for the critical program components; carrying out an exploration phase for exploring a parameter range in relation to the optimizable program parameters, the robot program being carried out multiple times, the parameter range being scanned for the critical program components and trajectories of the robot being recorded such that training data are present for the critical program components; carrying out a learning phase in order to generate component representatives for the critical program components of the robot program on the basis of the training data collected in the exploration phase, wherein a component representative represents a system model which, in the form of a differentiable function, maps a specified state of the robot and specified program parameters to a predicted trajectory; carrying out an inference phase for determining optimized program parameters for the critical program components of the robot program, wherein optimizable program parameters of the component representative are iteratively optimized in respect of a specified target function by means of a gradient-based optimization method using the component representative. The invention furthermore relates to a corresponding system.

A control device sets a relative relation amount between a plurality of target objects that are to be final objectives, repeatedly acquires observation data from a sensor and calculates the relative relation amount between the plurality of target objects existing in the environment from the acquired observation data. Further, the control device determines a series of the relative relation amounts in a state that is to be an objective from the relative relation amount at a time point at which control of the behavior starts until the relative relation amount as the final objectives is realized, and repeatedly determines control instructions so as to change the relative relation amount in a present state calculated from the latest observation data into the relative relation amount in a state of an objective to be transitioned to next. Then, the control device outputs the determined control instruction to a robot device.

Provided are systems and methods for decomposing learned robotic activities into smaller sub-activities that can be used independently. In one example, a method may include storing simulation data comprising an activity of a robot during a training simulation performed via a robotic simulator, decompose the activity into a plurality of sub-activities that are performed by the robot during the training simulation based on changes in behavior of the robot identified within the simulation data, and generating and storing a plurality of programs for executing the plurality of sub-activities, respectively, in the storage.

Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

A system for object processing is disclosed. The system includes a framework of processes that enable reliable deployment of artificial intelligence-based policies in a warehouse setting to improve the speed, reliability, and accuracy of the system. The system harnesses a vast number of picks to provide data points to machine learning techniques. These machine learning techniques use the data to refine or reinforce in-use policies to optimize the speed and successful transfer of objects within the system. For example, objects in the system are identified at a supply location, a predetermined set of information regarding object is retrieved and combined with a set of object information and processing parameters determined by the system. The combined information is then used to determine routing of the object according to an initial policy. This policy is then observed, altered, tested, and re-implemented in an altered form.

To generate a more appropriate path, provided is a robot path generation device including circuitry configured to: hold a track planning module learning data set, in which a plurality of pieces of path data generated based on a motion constraint condition of a robot, and evaluation value data, which corresponds to each of the plurality of pieces path data and is a measure under a predetermined evaluation criterion, are associated with each other; and generate, based on a result of a machine learning process that is based on the track planning module learning data set, a path of the robot between a set start point and a set end point, which are freely set.