Abstract: A controller for controlling an entity is provided. The controller comprises a memory to store a hierarchical multimodal reinforcement learning (RL) neural network, and a processor. The hierarchical multimodal RL neural network includes a first level controller and two second level controllers. Each of the second level controllers comprise a first sub level controller relating to a first modality and a second sub level controller relating to a second modality. The first modality is different from the second modality. The processor is configured to select one of the two second level controllers to perform a first sub-task relating to a task, using the first level controller, based on input data and a state of the hierarchical multimodal RL neural network. The selected second level controller is configured to determine a set of control actions to perform the first sub-task, and control the entity based on the set of control actions.

Abstract: Cloud-enabled and artificial intelligence (AI) based biosignal systems and methods are described for the coaching of users to enhance biosignal enabled devices based on device usage. The systems and methods are comprised of, and/or utilize, a cloud based server to aggregate biosignal data from biosignal enabled devices, train an enhanced AI based coaching model using the biosignal data, and to provide the enhanced AI based coaching model to the biosignal enabled devices. The biosignal enabled devices replace a first AI coaching model with the enhanced AI based coaching model, and input user-specific biosignal data to the enhanced AI based coaching model to output a device usage classification. Based on the device usage classification, the systems and methods initiate a coaching procedure that coaches the user how to use or configure the biosignal enabled device to implement an updated configuration for the biosignal enabled device that is optimized for the user.

Abstract: A method identifies an anomaly condition in operating a hand-held, mechanically unconstrained master device for controlling a robotic system for medical or surgical teleoperation. The method includes detecting or calculating the velocity vector of a point belonging to or integral with the master device, or of a virtual point uniquely and rigidly associated with the master device. A detectable anomaly condition is identified and recognized and/or discriminated based on the detected velocity vector, or based on a vector component. The detectable anomalies include master device excessive angular or linear velocity, inability to follow by the slave device, excessive vibrations or involuntary or abnormal opening of the master device. Each detectable anomaly is associated with a system state change to be performed if the anomaly is detected. The state change includes exiting or suspension from the teleoperation state. A robotic system for medical or surgical teleoperation performs the method.

Abstract: A vehicle device comprising a base vehicle and a seat unit being releasably connectable to the base vehicle is described. The base vehicle comprises an electronic control means and a vehicle-side wireless communication means, and the seat unit comprises at least one sensor, a battery, an electronic unit, and a seat-side wireless communication means. In order to provide the electronic control means of the base vehicle with the necessary information about the seat unit in an energy-saving manner, the electronic unit reads-out the status of the at least one sensor in a certain time-scheme and transmits a sensor related signal via the seat-side wireless communications means only if the status of the sensor changed since the previous read-out.

Abstract: This robot system includes: an automated guided vehicle that includes a support surface and automatically travels; a robot cell including a seat surface to be mounted on the support surface, a ground contact portion protruding downward from the seat surface so as to contact with a ground, an articulated arm, and a robot controller that controls operation of the articulated arm; and a switching mechanism that performs switching between a transferable state in which the seat surface is mounted on the support surface and the ground contact portion is separated from the ground, and a placed state in which the seat surface is separated from the support surface and the ground contact portion contacts with the ground.

Abstract: The present application relates to a computer-implemented medical method of determining a compensation for gravity-related displacements of a medical carrier structure having at least one adjustable and selectively fixable joint which respectively connects two sections of the carrier structure. The present application further relates to a corresponding computer program and medical system.

Abstract: A method and apparatus for interworking between an autonomous delivery robot and a transportation infrastructure are disclosed. A method of operating a delivery robot service provider that manages a delivery robot, the method may include: generating delivery information in response to a delivery request from a user; assigning a delivery robot that is to perform the delivery request; transmitting the delivery information to the delivery robot; checking whether the delivery robot arrives at a transportation infrastructure located on a delivery route based on delivery status information transmitted from the delivery robot; and transmitting signal request information associated with the transportation infrastructure to a traffic information service provider that manages the transportation infrastructure to allow the delivery robot to use the transportation infrastructure.

Abstract: Systems and methods for calculating an insertion point and a path for a rod are provided. A surgical plan having at least one image and information about a position of at least one tower may be received. The at least one image may depict a surgical region. A soft tissue portion and at least one anatomical element may be identified in the at least one image. An insertion point and a path from the insertion point to the at least one tower may be calculated based on the identified soft tissue portion and at least one anatomical element. The rod may be inserted at the insertion point and along the path.

Abstract: The present invention relates to a substrate transfer system and method enabling a direction of a substrate or the order of substrates to be maintained even when the substrate is swing-moved and transferred by a robot transportation device, in particularly, the substrate transfer system may include: a robot transportation device that transfers at least one substrate using at least one swing-movable transport arm; and a compensatory rotation device that is mounted on the transport arm of the robot transportation device and selectively supports the substrate to thus enable compensatory rotation thereof so that, even when the transport arm has a swing motion while the substrate is transferred by the robot transportation device, a direction of the substrate or the order of the substrates can be maintained.

Abstract: A system for the safe control of safety protections comprises at least one first control device (2) placed outside the safety perimeter (P) for sending commands to stop and enable the machine or plant (M) following the opening/closing of the accesses (A1, A2), a first safety switch (3) placed close to one or more of the accesses (A1, A2) for their locking and/or unlocking, one or more actuators having a transponder with identification code for interacting with the first control device and/or safety switch, at least one control unit connected to the first control device and to the safety switch to receive the actuation commands and enable the operation of the machine or plant (M) between an operating condition and a safety operating condition. Second means are also provided for enabling the exit from the safety perimeter (P) for one or more operators.

Abstract: Example implementations may relate to determining a strategy for a drop process associated with a light detection and ranging (LIDAR) device. In particular, the LIDAR device could emit light pulses and detect return light pulses, and could generate a set of data points representative of the detected return light pulses. The drop process could involve a computing system discarding data point(s) of the set and/or preventing emission of light pulse(s) by the LIDAR device. Accordingly, the computing system could detect a trigger to engage in the drop process, and may responsively (i) use information associated with the environment around the vehicle, operation of the vehicle, and/or operation of the LIDAR device as a basis to determine the strategy for the drop process, and (ii) engage in the drop process in accordance with the determined strategy.

Abstract: A cleaning robot control method, applicable to a cleaning robot, includes: obtaining a network status of the cleaning robot and performing a preset action when the network status is a network-disconnected state or a network signal intensity is lower than a preset signal intensity threshold. A computer-readable storage medium and a cleaning robot are further provided.

Abstract: This provides a system and method for handling the interchange of trailers between an over the road (OTR) truck and an autonomous vehicle (AV) yard truck in a facility yard includes an interchange zone (IZ) that is bounded by a predetermined boundary structure, having an OTR entry gate and an OTR exit gate on a first side and an AV entry gate and an AV exit gate on a second side. The system and method further includes a management process that selectively opens and closes each of the OTR entry gate, the OTR exit gate, the AV entry gate and the AV exit gate according to a predetermined set of rules.

Abstract: A method and a system for controlling a flight device, a storage medium and an electronic device are provided. The method includes: acquiring a mission flight route of a first flight device, where the mission flight route is configure to indicate a flight route of a data acquisition mission to be performed by the first flight device; generating a relay flight route of the second flight device according to the mission flight route and a relay base station distribution on the mission flight route, where the relay flight route is configured to indicate a flight route of the second flight device during execution of the data acquisition mission by the first flight device; and controlling the first flight device to perform the data acquisition mission according to the mission flight route and controlling the second flight device to perform the data acquisition mission according to the relay flight route.

Abstract: A method and a device for controlling mode switching of a hybrid electric vehicle, and a vehicle is provided, and belongs to the field of hybrid electric vehicles. The method includes: performing, if the drive state information indicates that a current drive mode of the hybrid electric vehicle is a forward mode of a non-hybrid drive and in a case that a current speed reaches a speed limit, a pre-gear operation when a transmission gear of the hybrid electric vehicle is a neutral gear, to switch the transmission gear from the neutral gear to a second gear. The technical solution provided by the embodiments of the present disclosure can make the hybrid electric vehicle unable to switch to the hybrid drive mode due to the limitation of the ability of synchronizer on gear shifting when driving at a high speed.

Abstract: Disclosed herein relates to a system of and method for solid-state microwave amplification by stimulated emission of radiation (hereinafter “MASER”) and/or a sound amplification by stimulation emission of radiation (hereinafter “SASER”) used in a series of micro-drones to for monitoring, protecting, controlling, disabling, sterilizing, and/or destroying of a target. The micro-drones may form an autonomous, self-sustaining swarm, such that the micro-drones may exit and rejoin the hybrid drone swarm, automatically, optimizing monitoring by allowing at least one micro-drone to be constantly within the hybrid drone swarm around the target without requiring downtime. Additionally, the micro-drones may automatically recharge via at least one solar panel. In addition, the present disclosure may defend a user and/or area from enemy drones or enemy targets using a system of micro-drones.

Abstract: A system and method for utilizing model predictive control for optimal interactions that include receiving environment e data associated with a surrounding environment of an ego agent and dynamic data associated with an operation of the ego agent. The system and method also include inputting the environment data and the dynamic data to variational autoencoders. The system and method additionally include utilizing the model predictive control through functional approximation with the variational autoencoders and decoders to output probabilistic action estimates. The system and method further include outputting an estimated optimal control trajectory based on analysis of the probabilistic action estimates to control at least one system of the ego agent to operate within the surrounding environment of the ego agent.

Abstract: A system and a method for providing a sign language service are provided. The system includes a first terminal that generates at least one piece of first message data corresponding to a message to be delivered by a first user. The system also includes a server that converts the first message data received from the first terminal into first operation data corresponding to an operation of a robot. The system also includes the robot that performs an operation according to the first operation data received from the server. The server sorts two or more pieces of first operation data based on a transmission order according to a predetermined criterion, when identifying the two or more pieces of first operation data, and transmits the pieces of sorted first operation data to the robot. The robot performs the operation, based on the pieces of sorted first operation data.

Abstract: The present disclosure provides to an apparatus for managing travel of a vehicle having an autonomous travel function. The apparatus executes the following steps. The apparatus sequentially acquires sensor information from a recognition sensor mounted on the vehicle. The apparatus sequentially generates prediction information showing a position of an object at a future time point based on the sensor information acquired sequentially. The apparatus transmits a remote support request to a remote support operator. The apparatus receives a remote support given in response to the remote support request by the remote support operator. The apparatus makes the vehicle autonomously travel in accordance with the remote support in response to confirming that an actual position of an object obtained from sensor information and a predicted position of an object obtained from prediction information correspond.

Abstract: A robot management system includes: a first robot management unit that manages an activity of a first mobile robot taking a first area as an activity range; a second robot management unit that manages an activity of a second mobile robot taking a second area as an activity range; a wide area task accepting unit that accepts a wide area task involving movement from a first point in the first area to a second point in the second area; and a narrow area task setting unit that sets a first narrow area task including movement from the first point in the first area to a relay point in an overlap area and takeover processing to the second mobile robot at the relay point for supporting the second mobile robot to move to the second point, and a second narrow area task including the takeover processing from the first mobile robot 61 at the relay point.