A self-position estimation model learning device (10) includes: an acquisition unit (30) that acquires, in time series, a local image captured from a viewpoint of a self-position estimation subject in a dynamic environment, and a bird's-eye view image which is captured from a location overlooking the self-position estimation subject and is synchronized with the local image; and a learning unit (32) for learning a self-position estimation model that takes the local image and the bird's-eye view image acquired in time series as input, and outputs the position of the self-position estimation subject.

An apparatus has a memory storing a reinforcement learning policy with an optimization component and a data collection component. The apparatus has a regularization component which applies regularization selectively between the optimization component of the reinforcement learning policy and the data collection component of the reinforcement learning policy. A processor carries out a reinforcement learning process by: triggering execution of an agent according to the policy and with respect to a first task; observing values of variables comprising: an observation space of the agent, an action of the agent; and updating the policy using reinforcement learning according to the observed values and taking into account the regularization.

A method includes determining motion imitation information for causing a system to imitate a physical task using a first machine learning model that is trained using motion information that represents a performance of the physical task, determining a predicted correction based on the motion information and a current state from the system using a second machine learning model that is trained using the motion information, determining an action to be performed by the system based on the motion imitation information and the predicted correction; and controlling motion of the system in accordance with the action.

A method for recommending a drilling target of a new well based on cognitive computing is provided, including: establishing a reservoir geological model; acquiring a dynamic parameter and a static parameter; establishing multiple fuzzy rules bases; inputting the dynamic and static parameters into the fuzzy rules base to obtain aggregated output fuzzy sets of membership values; defuzzifying the fuzzy set of the membership values to obtain crisp values of the fuzzy variables; inputting the crisp values into the fuzzy rules base to obtain a aggregated output fuzzy set of DA membership values of drilling attractiveness DA as a fuzzy variable; defuzzifying the DA to obtain a score of the DA; establishing a drilling attractiveness region with a radius R by taking each grid as a center; calculating region drilling attractiveness RDA score of the region; and determining a region with a highest score as the location of the new well.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, at each of multiple time steps, sensor data captured by an onboard sensor of a drone at the time step, providing an input including the sensor data to a drone control neural network having a brain emulation sub-network with an architecture that is specified by synaptic connectivity between neurons in a brain of a biological organism, including instantiating a respective artificial neuron in the brain emulation sub-network corresponding to each of multiple biological neurons in the brain of the biological organism, and instantiating a respective connection between each pair of artificial neurons, processing the input using the drone control neural network to generate an action selection output, and selecting an action to be performed to control the drone at the time step based on the action selection output.

Disclosed herein are a method for driving a robot based on an external image, and a robot and a server implementing the same. In the method, and the robot and server implementing the same, drive of a robot is controlled further using external images acquired by camera modules installed outside the robot. To this end, a robot according to an embodiment of the present disclosure includes a communication unit configured to communicate with external camera modules acquiring external images including the robot that is being driven, a drive-information acquiring unit configured to acquire driving related information at the time of driving the robot, a driving unit configured to drive the robot, and a control unit configured to control the driving unit using external information including the external images received from the external camera modules and the driving related information.

An automated robot design pipeline facilitates the overall process of designing robots that perform various desired behaviors. The disclosed pipeline includes four stages. In the first stage, a generative engine samples a design space to generate a large number of robot designs. In the second stage, a metric engine generates behavioral metrics indicating a degree to which each robot design performs the desired behaviors. In the third stage, a mapping engine generates a behavior predictor that can predict the behavioral metrics for any given robot design. In the fourth stage, a design engine generates a graphical user interface (GUI) that guides the user in performing behavior-driven design of a robot. One advantage of the disclosed approach is that the user need not have specialized skills in either graphic design or programming to generate designs for robots that perform specific behaviors or express various emotions.

Certain aspects of the present disclosure provide techniques for training and inferencing with machine learning localization models. In one aspect, a method, includes training a machine learning model based on input data for performing localization of an object in a target space, including: determining parameters of a neural network configured to map samples in an input space based on the input data to samples in an intrinsic space; and determining parameters of a coupling matrix configured to transport the samples in the intrinsic space to the target space.

The present invention provides a robot control method, and the method includes: collecting interaction information of a companion target, and obtaining digital person information of a companion person (101), where the interaction information includes interaction information of a sound or an action of the companion target toward the robot, and the digital person information includes a set of digitized information of the companion person; and determining, by using the interaction information and the digital person information, a manner of interacting with the companion target (103); generating, based on the digital person information of the companion person and by using a machine learning algorithm, an interaction content corresponding to the interaction manner (105); and generating a response action toward the companion target based on the interaction manner and the interaction content (107).

A machine learning device, which learns an operation program of a robot, includes a state observation unit which observes as a state variable at least one of a shaking of an arm of the robot and a length of an operation trajectory of the arm of the robot; a determination data obtaining unit which obtains as determination data a cycle time in which the robot performs processing; and a learning unit which learns the operation program of the robot based on an output of the state observation unit and an output of the determination data obtaining unit.