A wearable system includes an exosuit or exoskeleton; an actuator(s) configured to generate force in the exosuit or exoskeleton; a sensor(s) configured to measure information for evaluating an objective function associated with providing physical assistance to the wearer, an interaction between the wearer and the exosuit or exoskeleton, and/or an operation of the exosuit or exoskeleton; and a controller(s) configured to: actuate the actuator(s) according to an actuation profile(s), evaluate the objective function based on the information measured by the at least one sensor to determine a resulting change in the objective function, adjust a parameter(s) of the actuation profile(s) based on the resulting change in the objective function, and continue to actuate, evaluate, and adjust to optimize the actuation parameter(s) for maximizing or minimizing the objective function. Wearable systems configured to assist or promote an improvement in the wearer's gait and optimized using a gradient descent or Bayesian approach.

A method for planning a manipulation task of an agent, particularly a robot. The method includes: learning a number of manipulation skills wherein a symbolic abstraction of the respective manipulation skill is generated; determining a concatenated sequence of manipulation skills selected from the number of learned manipulation skills based on their symbolic abstraction so that a given goal specification indicating a given complex manipulation task is satisfied; and executing the sequence of manipulation skills.

According to examples, an apparatus may include a processor and a memory on which is stored machine readable instructions that may cause the processor to access data about an environment of an agent, identify an actor in the environment, and access candidate models, in which each of the candidate models may predict a certain action of the identified actor. The instructions may also cause the processor to apply a selected candidate model of the accessed candidate models on the accessed data to determine a predicted action of the identified actor and may implement a recursive reinforcement learning model using the predicted action of the identified actor to determine an action that the agent is to perform. The instructions may further cause the processor to cause the agent to perform the determined action.

A computer-implemented method includes establishing, by a computer device, an activity to be performed by a robot; determining, by the computer device, a required knowledge that is required for the robot to perform the activity; comparing, by the computer device, the required knowledge to a current knowledge of the robot to establish an additional learning that is needed for the robot to perform the activity; requesting, by the computer device, the additional learning; directing, by the computer device, retrieval of the additional learning to the robot if the additional learning is available for retrieval; and requesting, by the computer device, that the additional learning be created if the additional learning is not available for retrieval.

A robot control apparatus for a more precise seam tracking operation, includes: a storage unit in which teaching data is stored; an accepting unit that accepts a sensing result of a laser sensor, from a robot including a working tool and the laser sensor attached to the working tool and configured to detect a shape of a working target before an operation of the working tool; and a control unit that moves the working tool based on the teaching data, corrects the movement of the working tool based on the sensing result, and adjusts an angle about a tool axis such that an operation point indicated by the sensing result is at a center of a field of view of the laser sensor. Accordingly, an operation line can be detected near the center of the field of view of the laser sensor, and thus more precise detection is possible.

A system includes a neural network system implemented by one or more computers. The neural network system is configured to receive an observation characterizing a current state of a real-world environment being interacted with by a robotic agent to perform a robotic task and to process the observation to generate a policy output that defines an action to be performed by the robotic agent in response to the observation. The neural network system includes: (i) a sequence of deep neural networks (DNNs), in which the sequence of DNNs includes a simulation-trained DNN that has been trained on interactions of a simulated version of the robotic agent with a simulated version of the real-world environment to perform a simulated version of the robotic task, and (ii) a first robot-trained DNN that is configured to receive the observation and to process the observation to generate the policy output.

The present technology relates to a control device, a control method, and a program capable of enabling predetermined motion while a gripped object is stabilized. A control device according to one aspect of the present technology is a device that detects a gripped state of an object gripped by a hand unit, and limits motion of a motion unit while the object is gripped by the hand unit, in accordance with a result of detection of the gripped state. The present technology can be applied to a device that controls a robot including a hand unit capable of gripping an object.

The present technology relates to an autonomous mobile body, an information processing method, a program, and an information processing device that enable a user to experience discipline for the autonomous mobile body. The autonomous mobile body includes: a recognition unit that recognizes an instruction given; an action planning unit that plans an action on the basis of the instruction recognized; and an operation control unit that controls execution of the action planned, in which the action planning unit changes a detail of a predetermined action as an action instruction that is an instruction for the predetermined action is repeated. The present technology can be applied to a robot, for example.

A robot-connected IoT-based sleep-caring system includes a sleep-caring robot and an IoT system. The sleep-caring robot includes environment monitoring, physiology monitoring, sleep monitoring, sound, lighting and electricity control, a smart storage compartment, central data processing, and machine arms. The IoT system senses and executes instructions from the sleep-caring robot, thereby catering to bedroom activities of the user.

A communication robot includes: an operation part; and a communication arbitration unit configured to exhibit a robot mode for autonomously operating the operation part by applying a first operational criterion and an avatar mode for operating the operation part based on an operation instruction sent from a remote operator by applying a second operational criterion to arbitrate communication among three parties, that is, the robot mode, the avatar mode, and a service user.