Abstract: For control about a remote center of motion (RCM) of a surgical robotic system, possible configurations of a robotic manipulator are searched to find the configuration providing a greatest overlap of the workspace of the surgical instrument with the target anatomy. The force at the RCM may be measured, such as with one or more sensors on the cannula or in an adaptor connecting the robotic manipulator to the cannula. The measured force is used to determine a change in the RCM to minimize the force exerted on the patient at the RCM. Given this change, the configuration of the robotic manipulator may be dynamically updated. Various aspects of this RCM control may be used alone or in combination, such as to optimize the alignment of workspace to the target anatomy, to minimize force at the RCM, and/or to dynamically control the robotic manipulator configuration based on workspace alignment and force measurement.

Abstract: Methods and systems for assisting a vehicle in avoiding an object in a roadway and communicating associated information to trailing vehicles. Image data is sensed by a vehicle image sensor regarding a roadway. A computing system detects an object in the roadway based on the first image data. Feature extraction is performed to extract relevant features of the object, which is fed to an object classification model to determine a class of the object. A threat analysis is performed based on the determined class of the object, outputting a risk score. The first vehicle is commanded to take an action based on the risk score. The class of the object, the risk score, and/or the commanded action taken by the vehicle is communicated to a second vehicle that is approaching the object.

Abstract: A method and system for robot skill learning applicable to high precision assembly tasks employing a compliance controller. An actor-critic reinforcement learning controller is coupled to the compliance controller, where an actor neural network provides target position adjustment action data to the compliance controller based on robot state data feedback, and a critic neural network is used to train the actor. The critic neural network receives the robot state data feedback and reward data from the robot, along with the action data from the actor, and correlates optimal actions associated with states in order to maximize the reward. The critic then adjusts the parameters of the actor so that the actor produces effective actions in response to the state data, leading to rapid and reliable completion of the assembly task by the compliance controller/robot system. The critic is no longer used after the actor is adequately trained.

Abstract: The present disclosure relates to a computer-implemented method for learning operators for planning a behavior of an autonomous device. The method includes obtaining a set of training data including observations of a plurality of skills executable by the autonomous device in an interaction with at least one entity for addressing a first task, obtaining a predetermined set of data defining a hierarchy of entities including the at least one entity, learning a set of individual skills based on the obtained set of training data, generating a set of generalized skills by generalizing the learned set of individual skills based on the predetermined set of data that defining a hierarchy of entities, performing behavior planning of the autonomous device for addressing a second task different from the first task based on the generalized set of skills.

Abstract: A system for companion robot with 3D display device and a method are disclosed. In the system, a companion robot continuously senses a user behavior status and an input speech, converts the input speech to a text, transmits the text and the user behavior status to finite state machines of a server-end host to perform parsing and transition, so that the server-end host generates a chat message having an emotion label, transmits the chat message to an AI device, receives and stores the companion conversation message to a companion conversation list; the companion robot selects companion conversation message from the companion conversation list as an output message, and convert the output message to speech which is broadcasted by a speaker; while broadcasting the output message, the companion robot continuously obtains image data from a multi-source image and outputs the image data to a 3D display device for displaying.

Abstract: Systems and techniques for controlling a mobile robot. In an example, the system may include a processor and memory, including instructions, which when executed by the processor, cause the processor to determine a state of the mobile robot. The state of the mobile robot may be determined using at least one of: data provided by the mobile robot or data captured by one or more sensors proximate to or attached to the mobile robot. The system may determine a state of an object proximate to the mobile robot using the data captured by the one or more sensors, and identify information relating to one or more available stopping points. The system may identify a condition of the mobile robot that requires the mobile robot to stop and issue a command to the mobile robot to navigate to a particular one of the one or more available stopping points.

Abstract: Systems and methods for passive robot-mediated physical human-human interaction using hierarchical constraints. The system enforces constraints on both sides of a bilateral physical interaction with different priorities on each side in the presence of time-varying destabilizing factors such as control system limitations, human variability, hard contacts, relaxed user grasps, stiff control settings, and/or communication delays. A hierarchical optimization framework is provided to satisfy these constraints. A back-up passivity control may also be included to ensure optimization at both sides.

Abstract: The various embodiments described herein generally relate to systems and methods for operating one or more self-driving vehicles. In some embodiments, the self-driving vehicles may include a vehicle processor being operable to: control the vehicle to navigate an operating environment in an initial vehicle navigation mode; monitor for one or more trigger conditions indicating a possible change for the vehicle navigation mode; detect a trigger condition; determine a prospective vehicle navigation mode associated with the detected trigger condition; determine whether to change from the initial vehicle navigation mode to the prospective vehicle navigation mode; and in response to determining to change from the initial vehicle navigation mode to the prospective vehicle navigation mode, adjust one or more vehicle attributes corresponding to the prospective vehicle navigation mode, otherwise continue to operate the vehicle in the initial vehicle navigation mode.

Abstract: A computer-implemented method includes generating a joint-torque-limit model for the articulated arm based on allowable joint torque sets corresponding to a base pose of the base. The method also include receiving a first requested joint torque set for a first arm pose of the articulated arm and determining, using the joint-torque-limit model, an optimized joint torque set corresponding to the first requested joint torque set. The method also includes receiving a second requested joint torque set for a second arm pose of the articulated arm and generating an adjusted joint torque set by adjusting the second requested joint torque set based on the optimized joint torque set. The method also includes sending the adjusted joint torque set to the articulated arm.

Abstract: The present disclosure relates to a computer-implemented method of synthesising a training dataset for training a comparison function of a machine learning service in the detection of a multi-pick event in which a robotic manipulator erroneously picks two or more items concurrently, the method comprising: selecting first image data representative of an image of a plurality of items to be picked by the robotic manipulator; selecting intermediate image data representative of an image of the plurality of items following the removal, by the robotic manipulator, of an item from the plurality of items; selecting final image data representative of an image of the plurality of items following the removal, by the robotic manipulator, of another item from the plurality of items; and, generating the training dataset representative of a notional multi-pick event based on a sequence of unlabelled image data consisting of the first and final image data.

Abstract: A method for a scene interpretation of an environment of a vehicle. The method includes: receiving environment sensor data from at least one environment sensor of a vehicle; carrying out an object detection based on the environment sensor data and detecting first objects in the environment of the vehicle; carrying out a scene analysis of the environment by taking into consideration the detected first objects and second objects stored in a map display of the environment, the scene analysis including: comparing the first objects detected in the object detection based on the environment sensor data to the second objects of the map display; and supplying a scene interpretation based on the scene analysis to a vehicle control of the vehicle, and at least the first objects detected in the object detection that agree with corresponding second objects of the map display are considered in the scene interpretation.

Abstract: A vehicle drive assist apparatus is to be applied to a vehicle. The vehicle drive assist apparatus includes an object recognizer, a risk area setter, and a risk level setter. The object recognizer is configured to recognize an object in front of the vehicle. The risk area setter is configured to, when small objects are around the object, set a risk area including the small objects. The risk level setter is configured to set a risk level for the risk area with respect to the vehicle based on distribution of height information items within the risk area.

Abstract: A system according to at least one embodiment of the present disclosure includes a processor; and a memory coupled with the processor and including data stored thereon that, when processed by the processor, enables the processor to: predict, at a first time, a motion of an object during a surgical procedure and at a second time following the first time; and update, based on the predicted motion of the object, a surgical navigation path of a robotic arm.

Abstract: A method and teleoperation system, includes provision of first information on an environment of a teleoperated device by at least one sensor module that is included in the teleoperated device and prediction of an action intended by the operator based on an input of the operator by an action predictor module that is included in the information gathering assistant module. It is determined whether first information on an environment is sufficient to execute the intended action in the environment by a reasoning agent module. Then second information on the environment is determined, which is suitable to enhance the environment information which is useful to execute the intended action in the environment by the reasoning agent module. Provision of second information is controlled by at least one information provision unit, and the first and second information on the environment is fused by an information fusion module.

Abstract: Provided is a vehicle integrated control method used for a vehicle integrated control system, wherein the vehicle integrated control system at least can comprise an integration module and a plurality of control modules, and the integration module is provided inside a vehicle. The method comprises: in response to a target operation performed by a user on the integration module, determining a target control instruction corresponding to the target operation; determining a target control module corresponding to the target control instruction, the target control module being at least one of the plurality of control modules; and activating the target control module to cause the target control module to control the enabling or disabling of a corresponding function on the basis of attribute information of internal and external environments of the vehicle. Also disclosed are a vehicle integrated control apparatus, a device, and a storage medium.

Abstract: An autonomous driving control method receives a HD map and extracts a HD road boundary and a HD lane line based on the HD map. A real-time map displaying a road driving environment of a vehicle is generated using sensor information detected by a sensor mounted on the vehicle. A real-time road boundary and a real-time lane are extracted based on the generated real-time map. The HD road boundary is compared to and analyzed from the real-time road boundary, and the HD lane line is compared and analyzed to the real-time lane. It is determined whether the HD map has changed based on the analyzed result value.

Abstract: System, methods, and other embodiments described herein relate to improving the sensing and lighting coverage of a first vehicle using a second vehicle. In one embodiment, a method includes determining at least one of a sensor coverage and a lighting coverage of a first vehicle and a second vehicle. The method further includes controlling the second vehicle to park in a position that maximizes the at least one of the sensor coverage and the lighting coverage between the first vehicle and the second vehicle while the first vehicle is stationary. Moreover, the method includes activating at least one of sensors and lighting mechanisms of the first vehicle and the second vehicle.

Abstract: A method of automatic confinement of a land vehicle. The method includes defining a set of points of a track within which the vehicle is free to move, the track including at least one edge that defines a boundary of the track that must not be crossed by the vehicle determining a vehicle dynamic and position based on the information provided by plurality of sensors of the vehicle; calculating an intervention area of the track based on the current position and dynamic of the vehicle, and on the position from the at least one edge, the area to be avoided extending between the at least one edge of the track toward the current position of the vehicle within the track; determining whether the vehicle is at least partially in the intervention area; and controlling at least one actuator to modify the vehicle dynamic.

Abstract: A transporter network for determining robot actions based on sensor feedback can afford robots with efficient autonomous movement. The transporter network may exploit spatial symmetries and may not need assumptions of objectness to provide accurate instructions on object manipulation. The machine-learned model of the transporter network may also allow for learning various tasks with less training examples than other machinelearned models. The machine-learned model of the transporter network may intake observation data as input and may output actions in response to the processed observation data.

Abstract: An information processing apparatus includes a processor configured to simulate a virtual robot and a virtual image pickup apparatus moving in an interlocked manner with each other in a virtual space. The processor is configured to associate setting information of the virtual image pickup apparatus with a teaching point of the virtual robot.