Abstract: The present disclosure provides an object grasping method, an apparatus, a computer device and a storage medium, the method includes: in response to receiving a target object grasping instruction, determining a second confidence of each of candidate objects being a target object based on state description information of the target object and a first confidence of each of the candidate objects in a current scene having each preset state; determining a target candidate object and a reward information after performing each preset action for the target candidate object based on the first confidence and the second confidence; and determining a target preset action to be performed based on the reward information, and performing the target preset action.

Abstract: A system for object detection of a manufactured part. The system comprises a system controller electronically coupled to an image acquisition device and delivery mechanism. An electronically stored ordered object detection map is provided which comprises predetermined detectable objects associated with the manufactured part. The ordered object detection map is generated from output created by execution of a trained object detection model and by processing such output according to predetermined calibration criteria. The system causing a visual image of the manufactured part to be captured with image data being extracted and processed to render at least one of a pass determination and a fail determination. The system being configured to process the manufactured based upon the rendered pass/fail determination.

Abstract: A controller includes an input unit, an output unit, an input buffer, a processing unit, and a history log storage unit. The input unit receives from the user, an instruction for a robot. The output unit configured to output, to the user, a reaction from the robot to the instruction. The input buffer saves data of the instruction. The processing unit transmits a prompt to a natural language processing system, receives a response from the natural language processing system, generates an action command for the robot based on the response, and overwrites the data in the input buffer with an action performed by the robot. The history log storage unit stores a history log in which the data read from the input buffer and the response to the data is accumulated. The processing unit generates the prompt including the data read from the input buffer and the history log.

Abstract: In a travel assist system, a travel assist control unit selectively performs an off-peak task upon receiving at least one assistance request during an off-peak situation where there are a predetermined number of free operators included in a first group. The off-peak task assigns the at least one assistance request to a selected one of the free operators included in the first group. The travel assist control unit selectively performs an on-peak task upon receiving the at least one assistance request during an on-peak situation where there are not the predetermined number of the free operators included in the first group. The on-peak task analyzes assignment of the at least one assistance request to a selected one of second operators included in a second group in accordance with a priority level of the at least one assistance request.

Abstract: A method, system and computer program product for map-matching a probe to a point-of-interest (POI) during a trip by a vehicle in a region are disclosed. The method includes identifying POIs in the region; determining, for probes in the region, a latitude location of the probes, a longitude location of the probes and a data collection time stamp for the probes; determining, for each of the probes in the region, a proximity between the probes and the POIs within a predetermined radius of the probes; determining, for each of the POIs, a POI geographic coverage area; calculating an observed POI probability from the proximity and the POI geographic coverage area; and using a Hidden Markov Model to sequentially process the observed POI probability from a predetermined number of probes of the trip and to predict a most likely POI at which the probes are clustered.

Abstract: A surgical robotic arm includes a first link; a second link coupled to the first link at a first joint such that at least one of the first link or the second link is movable relative to each other; and a first actuator configured to move at least one of the first link or the second link. The surgical robotic arm also includes a joint torque sensor disposed within the first joint and configured to measure torque imparted on at least one of the first link or the second link to obtain a measured torque value. The surgical robotic arm further includes a controller configured to: determine an estimated joint torque value; compare the estimated joint torque value to the measured torque value; and determine an environmental torque value based on a comparison of the estimated joint torque value and the measured torque value.

Abstract: A system for generating navigation instructions for delivery of a cargo is provided. The system is configured to obtain geographic area information relating to a geographic area, determine cargo information relating to the cargo, determine one or more aerial routes for a delivery of the cargo based on the geographic area information and the cargo information, estimate a risk value for navigation of an aerial vehicle across each of the one or more aerial routes, identify an aerial route from the one or more aerial routes having lowest estimated risk value based on the estimated risk values for the one or more aerial routes, and generate the navigation instructions for navigation of the aerial vehicle along the identified aerial route for delivery of the cargo.

Abstract: A component of an edge server, including: processor circuitry; and a non-transitory computer-readable storage medium including instructions that, when executed by the processor circuitry, cause the processor circuitry to: distribute, to a client device, tokens that enable its end device to execute respective asynchronous adaptive motion primitives (A2MPs) of a task graph of a task, wherein an A2MP is a motion primitive of encoded motion factoring in motion updates from the end device; receive A2MP task execution status messages during execution of the A2MPs; and dynamically update the distribution of the token or the task graph based on the A2MP task execution status messages to modify a trajectory of the end device.

Abstract: A method for controlling an implement moved by an agricultural vehicle driving over a path along a crop row includes using a point cloud sensor to scan a portion of the crop row and to generate a point cloud. Multiple crop row volumes arranged along the portion of the crop row are determined. For each crop row volume, a vertical point density distribution is determined by determining which points of the point cloud fall within the crop row volume. The implement is controlled based on the vertical point density distribution of each crop row volume.

Abstract: Systems and methods for radar-based aircraft maneuver actions are provided. An example computer-implemented method includes transmitting, using one or more transmitters onboard an aircraft, one or more radio signals. Reflected radio data corresponding to one or more radio signals reflected from a plurality of radio detection and ranging (“radar”) reflectors placed at a plurality of locations associated with an aerial facility can be received using one or more radio receivers onboard the aircraft. A location for the aircraft can be computed based on the radio data and the plurality of locations associated with the aerial facility at which the radar reflectors are placed. A maneuver action for the aircraft can be initiated at a particular landing pad of the aerial facility based on the location.

Abstract: A method of executing a charging plan for at least one vehicle in a transportation system includes: receiving, at a charging infrastructure control system, operational state and energy consumption information for a plurality of network-enabled vehicles; predicting a geolocation of one or more vehicles of the plurality of network-enabled vehicles in a geographic region; allocating the one or more vehicles of the plurality of network-enabled vehicles to charging infrastructure in the geographic region; and optimizing, at an artificial intelligence system, a parameter of the charging plan based on the prediction of the geolocation of the one or more vehicles in the geographic region.

Abstract: A method of providing guidance, such as to the user of a personal mobility device, uses a head-worn device including a camera and one or more display devices. The method includes capturing images using the camera of the head-worn device and identifying an area, represented in the captured images, having a certain permission associated therewith. An augmented reality effect is overlaid on the area, and the captured images with the overlaid augmented reality effect are displayed on the head-worn device.

Abstract: A vehicle control apparatus includes: an approach detection section; a determination section; and an openable and closeable object operation control section. The approach detection section detects a person within a first detection range and a second detection range. The determination section determines whether or not a motion of a person detected by the approach detection section corresponds to an approach pattern in which the openable and closeable object is approached. The openable and closeable object operation control section brings an openable and closeable object operation unit into operation when the determination section determines that the motion corresponds to the approach pattern. When a person who is not detected within the first detection range is detected within the second detection range, the determination section determines that the motion of the person corresponds to the approach pattern.

Abstract: A method and associated system for operating a robotic visualization system comprising an imaging optical unit and a robotic arm for positioning the imaging optical unit within a surround. The method includes ascertaining a target field of view to be visualized by means of the imaging optical unit. Ascertaining a target pose of the robotic visualization system for capturing an image of the target field of view with a first imaging configuration of the imaging optical unit. Ascertaining a collision probability along a movement path of the robotic visualization system from a current pose to the ascertained target pose using a 3-D model of the surround. Ascertaining an adapted target pose for capturing an image corresponding to the target field of view with a second imaging configuration of the imaging optical unit using the 3-D model of the surround, should the ascertained collision probability exceed a predetermined threshold value.

Abstract: A layer module for integration into a handling robot system has an interface bank on the robot side, an interface bank on the handling side, and a third interface bank. The interface bank on the robot side has a geometric connection contour for position-centered fastening to an industrial robot of the robotic handling system or to a robot adapter part, along with a cable feed for receiving a fixed wiring of an electrical functional assembly arranged in the layer module to the industrial robot. The interface bank on the handling side has a geometric connection contour for position-centered releasable joining by a snap connection to a handling tool or to a layer module element connected upstream of the handling tool, along with a group of electrical contacts. The layer module enables the use of an industrial robot in combination with different handling tools and for changing handling tasks.

Abstract: A method for fulfilling a safety requirement of at least one vehicle in a driving situation at a point in time t. The method includes: determining a first safeguarded and position-dependent environment region of the vehicle; determining a second safety-relevant and position-dependent environment region of the vehicle; checking whether the second environment region is covered by the first environment region in the driving situation of the vehicle, and, if not, generating an item of environment region information of the vehicle based on the detected first and second environment regions and a perception function corresponding to the generation of each of the environment regions; transmitting the environment region information to an application; evaluating the environment region information by the application; and generating at least one item of suggestion information so that the safety requirement for the driving situation at the point in time t of the vehicle is fulfilled.

Abstract: A method for operating an autonomous mobile green space processing robot, wherein the green space processing robot includes a drive system for propulsion of the green space processing robot. The method includes: a) monitoring whether a sticking presumption criterion is met, wherein the sticking presumption criterion is characteristic of suspected sticking of the green space processing robot; b) if the sticking presumption criterion is met, operating the drive system for a movement change of the green space processing robot and monitoring whether a sticking confirmation criterion is met, wherein the sticking confirmation criterion is that the movement change does not occur; and c) if the sticking confirmation criterion is met, initiating a sticking countermeasure of the green space processing robot.

Abstract: This numerical control system 1 comprises: a numerical control device 5 that generates a machine-tool command signal, which is a command to a machine tool 2, in accordance with a machine-tool numerical control program, and generates a robot command signal, which is a command to a robot 3, in accordance with a robot numerical control program described on the basis of a robot coordinate system; and a robot control device 6 that controls an operation of the robot 3 on the basis of the robot command signal. The robot control device 6 acquires a coordinate value of the robot 3 in the robot coordinate system, and transmits the coordinate value as a reference coordinate value to the numerical control device 5. The numerical control device 5 generates the robot command signal on the basis of the reference coordinate value transmitted from the robot control device 6 and the robot numerical control program.

Abstract: A method is provided. The method includes performing a first stocking operation associated with a first shelving unit using a stocking vehicle. The first stocking operation includes a put operation including transferring a first product unit from a load support component of the stocking vehicle to a first storage location over the first shelving unit, or a get operation including transferring the first product unit from the first storage location over the first shelving unit to the load support component of the stocking vehicle. The method includes capturing, using a first image sensor coupled to the stocking vehicle, a first image of a view associated with a first predefined position of the first shelving unit during the first stocking operation. The method includes determining, based upon the first image, whether the first shelving unit is associated with a potential shift event.

Abstract: A vehicle control device that performs automatic driving without monitoring obligation is configured to: identity an obstacle which prevents the vehicle from traveling; identify, when the obstacle is identified, an avoidance measure which is a measure that allows the vehicle to avoid the obstacle; and permit, during the automatic driving without monitoring obligation, an avoidance based on a deviant measure on a basis of a fact that the avoidance measure is a deviant measure outside a scope of traffic regulations.