A method comprising obtaining, from a sensor, depth data representing a target object; selecting a model to fit to the depth data; for each data point in the depth data: defining a ray from a location of the sensor to the data point; and determining an error based on a distance from the data point to the model along the ray; when the depth data does not meet a similarity threshold for the model based on the determined errors, selecting a new model and repeating the error determination for the depth data based on the new model; when the depth data meets the similarity threshold for the model, selecting the model as representing the target object; and outputting the selected model representing the target object.

The relates to a method for operating a driver assistance unit of a motor vehicle using a navigation target specification device. A control unit operates by: receiving a target specification signal describing a projection on a trafficable driving surface; establishing the portion of the trafficable driving surface to which the light of the projection is applied as a driving target region; and, based on the received target specification signal, establishing a relative position of the motor vehicle relative to the driving target region. There is also a step of receiving an orientation signal from an orientation detection unit of the navigation target specification device, which describes a spatial target specification orientation of the navigation target specification device in the driving target region, on which basis a navigation target is established. Depending on the established relative position and the established navigation target, there is a step of establishing a movement path to the navigation target, a step of generating a navigation signal describing a controlling of the motor vehicle along the established movement path, and a step of transmitting the generated navigation signal to the driver assistance unit of the motor vehicle.

An adaptive region division method and system are provided. The adaptive region division method includes: building an environmental map based on laser radar data and odometer data, to determine information about an environment in which a target device is located (S11); performing feature extraction according to the laser radar data, to determine feature data, where the feature data includes line feature data and point feature data (S12); generating a virtual door according to the feature data and the information about the environment in which the target device is located (S13); and dividing a to-be-divided region where the target device is located according to the virtual door (S14). Therefore, a virtual door is generated according to laser data of a current environment to achieve the purpose of adaptive region division, so that the target device can more efficiently and quickly cover the whole space.

A work vehicle includes a first detection unit that detects an optical beam emitted from a beam projector disposed at one end of a reference travel path, a first position deviation calculation section that calculates position deviation by a vehicle body from the reference travel path based on a detection signal from the first detection unit, a second detection unit that detects a work boundary line that occurs due to work travel, a second position deviation calculation section that calculates position deviation of the vehicle body traveling along successive travel paths from the work boundary line based on a detection signal from the second detection unit, and a steering information generation section that, based on the position deviation calculated by the first position deviation calculation section and the second position deviation calculation section, generates steering information for correcting the position deviation.

A main server for controlling laser irradiation of a movement path of a robot, the main server including a communication unit configured to communicate with a camera module and a laser irradiation module; and a controller configured to: receive, via the communication unit, an image of a robot captured by the camera module, identify a location of the robot in the image captured by the camera module, generate a movement path of the robot based on sensing information, and transmit, via the communication unit, movement path information to the laser irradiation module for outputting the movement path to a vicinity of the robot with a laser for the robot to follow, in which the sensing information includes first information about an obstacle sensed by the camera module or second information about the obstacle sensed by the laser irradiation module.

A potential field generation unit 161 generates a potential field in which a local minimum point is not generated in a search range by making a potential distribution of the search range for searching a trajectory toward a target point asymmetric. For example, the potential field generation unit 161 generates an integrated potential field in which a potential distribution is asymmetric by integrating an offset potential field generated using an offset function to make the potential distribution asymmetric, a trajectory potential field in which potential decreases as a distance from the target point and a shortest trajectory to the target point decreases, and an obstacle potential field in which potential decreases as a distance from an obstacle increases. A trajectory planning unit 162 sets a plurality of trajectory candidates heading for the target point within a trajectory search range of a mobile body, and sets a trajectory candidate having a minimum moving cost calculated on the basis of the integrated potential field as an optimal trajectory. A highly stable trajectory plan can be easily created.

A reference pose of an object in a coordinate system of a map of an area is determined. The reference pose is based on a three-dimensional (3D) reference model representing the object. A first pose of the object is determined as the object moves with respect to the coordinate system. The first pose is determined based on the reference pose and sensor data collected by the sensor at a first time. A second pose of the object is determined as the object continues to move with respect to the coordinate system. The second pose is determined based on the reference pose, the first pose, and sensor data collected by the sensor at a second time consecutive to the first time.

Embodiments of the present disclosure disclose a docking apparatus, a mobile robot, and a docking method for the docking apparatus. The docking apparatus comprises a processor and a plurality of photosensitive devices electrically connected to the processor, wherein the processor determines, from the plurality of photosensitive devices, a photosensitive device receiving a laser light, the laser light being emitted by an opposite-end apparatus to be docked with the docking apparatus. The connection apparatus, according to a position offset between the photosensitive device receiving the laser light and a target photosensitive device, is controlled to move to a docking position calibrated by means of the target photosensitive device, such that the docking apparatus and the opposite-end apparatus are docked with each other. The embodiments help improve the accuracy of docking between the connection apparatus and the opposite-end apparatus.

Embodiments of the present application relate to the field of robots, and disclose a method and a device for automatically charging a robot, a charging station and a robot. The method for automatically charging a robot in the present application, applied to the robot, includes the steps of: detecting a distance to a charging station according to a laser ranging signal; starting laser feature recognition when the distance is determined less than a preset distance, where the laser feature recognition is configured to identify the charging station; and performing docking process according to a recognition result of the laser feature recognition, a laser ranging signal and an infrared guiding signal. The method for automatically charging a robot in the embodiments enables the intelligent robot to quickly and accurately find the charging station, and accurately perform the docking process and automatically charging.

A laser perception-based method for spatial positioning of an agricultural robot: erecting a laser radar with a ranging function in a positioning space, setting a three-dimensional coordinate system, and conducting scanning using the laser radar to obtain point cloud data of an object in the positioning space, where the point cloud data include an azimuth and a distance with respect to the laser radar; installing a laser receiver on the agricultural robot, receiving a laser radar signal using the laser receiver during movement, when a laser beam emitted by the laser radar irradiates the laser receiver, outputting laser signal data and elevation data from the laser receiver; conducting time-event matching on the laser signal data obtained by the laser receiver and the point cloud data scanned by the laser radar within each scanning period of the laser radar to obtain three-dimensional coordinates of a central position of the laser receiver.