Abstract: Vehicle alerts can be presented to the driver of a vehicle based on behaviors. It can be determined whether the driver will avoid an identified risk at a current location of the vehicle. Such a determination can be based on the past driving behavior of the driver and/or a general driving behavior of one or more other drivers. It can be determined whether to present an alert about the identified risk based on whether the driver will avoid the identified risk. In response to determining to that an alert about the identified risk should be presented, an intensity level for the alert can be determined. The alert can be caused to be presented to the driver at the determined intensity level.

Abstract: A domestic robotic system includes a moveable robot having an image obtaining device for obtaining images of the exterior environment of the robot, and a processor programmed to detect a predetermined pattern within the obtained images. The processor and image obtaining device form at least part of a first navigation system for the robot which can determine a first estimate of at least one of the position and orientation of the robot. A second navigation system for the robot determines an alternative estimate of the at least one of the position and orientation of the robot. Calibration of the second navigation system can be performed using the first navigation system.

Abstract: A robot and a method for controlling the robot detects a theft of the robot based on posture information for a main body of the robot and position information of the robot. Operation of the robot is restricted depending on whether a theft of the robot is detected.

Abstract: Embodiments herein describe a robotic system that uses range sensors to identify a vector map of an environment. The vector map includes lines that outline the shape of objects in the environment (e.g., shelves on the floor of a warehouse). The system identifies one or more line segments representing the boundary or outline of the objects in the environment using range data acquired by the range sensors. The robotic system can repeat this process at different locations as it moves in the environment. Because of errors and inaccuracies, line segments formed at different locations may not clearly align even when these line segments correspond to the same object. To account for this error, the robotic system match line segments identified at a first location with line segments identified at a second location. The matched line segments can be merged into a line that is stored in the vector map.

Abstract: Various examples are directed to systems and methods for routing an autonomous vehicle. For example, a system may access temporal data comprising a first temporal data item. The first temporal data item may describe a first roadway condition, a first time, and a first location. The system may also access a routing graph that comprises a plurality of route components and determine that a first route component of the routing graph corresponds to the first location. The system may generate a constrained routing graph at least in part by modifying the first route component based at least in part on the first roadway condition. The system may additionally generate a route for an autonomous vehicle using the constrained routing graph; and cause the autonomous vehicle to begin traversing the route.

Abstract: A device for detecting a failure of an actuator of a vehicle includes: a training device that trains a model using training data comprising behavior data of the vehicle and a steering compensation angle, and a controller that detects the failure of the actuator in the vehicle based on the model.

Abstract: A robot may include an input interface configured to obtain an image of a surrounding environment of the robot, and at least one processor configured to rotate the robot in place for localization, and estimate at least one of a position or a pose in a space, based on a plurality of sequential images obtained by the input interface during the rotation of the robot. The position or the pose of the robot may be estimated based on inputting the plurality of sequential images obtained during the rotation of the robot into a trained model based on an artificial neural network. In a 5G environment connected for the Internet of Things, embodiments of the present disclosure may execute an artificial intelligence algorithm and/or a machine learning algorithm.

Abstract: The present disclosure provides an action imitation method as well as a robot and a computer readable storage medium using the same. The method includes: collecting a plurality of action images of a to-be-imitated object; processing the action images through a pre-trained convolutional neural network to obtain a position coordinate set of position coordinates of a plurality of key points of each of the action images; calculating a rotational angle of each of the linkages of the to-be-imitated object based on the position coordinate sets of the action images; and controlling a robot to move according to the rotational angle of each of the linkages of the to-be-imitated object. In the above-mentioned manner, the rotational angle of each linkage of the to-be-imitated object can be obtained by just analyzing and processing the images collected by an ordinary camera without the help of high-precision depth camera.

Abstract: An in-vehicle environment setting system 10 includes: a receiving unit 210 that receives, from a vehicle 50, setting information regarding a setting for an in-vehicle environment of the vehicle 50 and environment information regarding an outdoor environment of the vehicle 50 in a manner associated with an identity of a user 52 who boards the vehicle 50; a learning unit 220 that learns a preference of the user 52 related to the setting for the in-vehicle environment based on the setting information and the environment information; a generation unit 230 that generates recommended setting information regarding a recommended setting for the in-vehicle environment preferred by the user 52 based on a learning result of the preference; and a transmission unit 240 that transmits the recommended setting information to a vehicle 60 which is different from the vehicle 50.

Abstract: Provided is a video display device wearable on the head of a user, wherein the video display device includes a video display unit capable of switching two or more display methods, a control unit for indicating a display method to the video display unit, a first detection unit for detecting the motion of the head of a user, a second detection unit for detecting the motion of the point of view of the user, and a motion determination unit for determining the motion state of the device user by using the output from the first detection unit and the output from the second detection unit. The control unit indicates a change of display methods to the video display unit in accordance with the determination result of the motion determination unit.

Abstract: The embodiment of the present disclosure provides a robot control method, a robot and a storage medium. In the embodiment of the present disclosure, the robot determines a position when the robot is released from being hijacked based on relocalization operation; determines a task execution area according to environmental information around the position when the robot is released from being hijacked; and afterwards executes a task within the task execution area. Thus, the robot may flexibly determine the task execution area according to the environment in which the robot is released from being hijacked, without returning to the position when the robot is hijacked, to continue to execute the task, then acting according to local conditions is realized and the user requirements may be met as much as possible.

Abstract: There is provided a control device including: a control unit that performs driving control of a vehicle. The control unit temporarily continues automated traveling of the vehicle on a basis of a surrounding environment estimated by a remaining function of a compound eye camera, in a case where a malfunction of the compound eye camera used in recognition of the surrounding environment is detected during execution of automated driving control for the vehicle.

Abstract: A robotic surgical system and method of operating the same. A manipulator supports a tool that has a TCP and manipulates a target bone. A navigation system has a localizer to monitor states of the manipulator and the target bone. Controller(s) determine commanded states of the TCP to move the tool along a cutting path relative to the target bone to remove material from the target bone. The controller(s) determine actual states of the TCP responsive to commanded movement of the tool along the cutting path, wherein each one of the commanded states of the TCP has a corresponding one of the actual states of the TCP for a given time step. The controller(s) compare the corresponding commanded and actual states of the TCP for one or more given time steps to determine a deviation and modify operation of the tool to account for the deviation.

Abstract: A steering control device is configured to control steering via a steering actuator of a vehicle. The steering control device includes a condition determination unit and a steering maintenance unit. The condition determination unit is configured to determine whether a maintenance condition required to keep a steering angle at a stop control angle is satisfied, the steering angle being given by the steering actuator to a tire of the vehicle, the stop control angle being the steering angle which is to be given at a stop position where the vehicle stops traveling. The steering maintenance unit is configured to keep the steering angle at the stop control angle in a pre-stop traveling section in which the vehicle travels until the vehicle arrives at the stop position after the maintenance condition is satisfied.

Abstract: The technology relates to route planning and performing driving operations in autonomous vehicles, such as cargo trucks, articulating buses, as well as other vehicles. A detailed kinematic model of the vehicle in evaluated in conjunction with roadgraph and other information to determine whether a route or driving operation is feasible for the vehicle. This can include evaluating a hierarchical set of driving rules and whether current driving conditions impact any of the rules. Driving trajectories and cost can be evaluated when pre-planning a route for the vehicle to follow. This can include determining an ideal trajectory for the vehicle to take a particular driving action. Pre-planned routes may be shared with a fleet of vehicles, and can be modified based on information obtained by different vehicles of the fleet.

Abstract: One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.

Abstract: A robotic work tool having a chassis, a cover and a controller for controlling the operation of the robotic work tool. The robotic work tool further has a lift/collision detection device (300) connected to the controller for providing sensor input, and which Hft/coUision detection device (300) includes a first sensor element (340) and a second sensor element (345). The controller (110) is configured to receive sensor input of a distance value indicating a distance between the first sensor element (340) and the second sensor element (345), determine that a lift has been detected, fay comparing the distance value with a lift detection threshold and/or determine that a collision has been detected, by comparing the distance value with a collision detection threshold, wherein the collision detection threshold is different from the lift detection threshold.

Abstract: Systems and methods for driver presence and position detection are disclosed herein. A method can include determining a presence and a position of a driver in a sensing zone of a vehicle using a sensor platform integrated into the vehicle, determining when the position of the driver indicates that the driver is not in a fully-seated position relative to a driver's seat of the vehicle, and selectively adjusting a vehicle parameter of the vehicle based on the driver not being in a fully-seated position.

Abstract: Image data from an image sensor is input into a predictive model to identify perimeter edges of a set of cuboidal items held on a pallet. Depth data from a depth sensor is used to identify a top surface of a first cuboidal item of the set of cuboidal items. Coordinates associated with corners of the first cuboidal item are identified using information about the perimeter edges and the top surface. The coordinates are used to generate instructions for a robotic manipulator to pick up the first cuboidal item.

Abstract: A force sensor that quantitatively detects an external force. The force sensor comprises a base unit, a displacement unit displacing by an external force, a first displacement sensor pair including two sets of sensors detecting a relative displacement between the base unit and the displacement unit in a first direction, and a second displacement sensor pair including two sets of sensors detecting a relative displacement between the base unit and the displacement unit in a second direction. Among four quadrants divided by two straight lines along each of the first direction and the second direction wherein, the straight lines passing through a midpoint of the two sets of sensors composing the first displacement sensor pair, the two sets of sensors composing the second displacement sensor pair are respectively disposed in two quadrants in which the two sets of sensors composing the first displacement sensor pair are respectively disposed.