Provided is a robot including a chassis; a set of wheels coupled to the chassis; a plurality of sensors; a processor; and a tangible, non-transitory, machine readable medium storing instructions that when executed by the processor effectuates operations. The operations include capturing, with an image sensor disposed on the robot, a plurality of images of an environment of the robot as the robot navigates within the environment; identifying, with the processor, an obstacle type of an obstacle captured in an image based on a comparison between features of the obstacle and features of obstacles with different obstacles types stored in a database; and determining, with the processor, an action of the robot based on the obstacle type of the obstacle.

Lighting control systems may be commissioned for programming and/or control with the aid of an autonomous mobile device. Design software may be used to create a floor plan of how the lighting control system may be designed. The design software may generate floor plan identifiers for each lighting fixture, or group of lighting fixtures. During commissioning of the lighting control system, the autonomous mobile device may be used to help identify the lighting devices that have been installed in the physical space. The autonomous mobile device may receive a communication from each lighting control device that indicates a unique identifier of the lighting control device. The unique identifier may be communicated by visible light communication (VLC) or RF communication. The unique identifier may be associated with the floor plan identifier for communication of digital messages to lighting fixtures installed in the locations indicated in the floor plan identifier.

This application relates to a navigation method and a navigation apparatus. The navigation method is executed by a mobile carrier and includes: moving along a preset guide trajectory body according to obtained target location information; and determining whether a current state of the mobile carrier is out-of-position, and in response to determining that the current state of the mobile carrier is out-of-position, obtaining current initialization location information of the mobile carrier after moving to a preset initialization tag. According to embodiments of the disclosure, reliable operation of the mobile carrier is ensured by re-initializing the mobile carrier in a case that an error occurs in the mobile carrier along the preset guide trajectory body.

A system may include one or more processors configured to receive a plurality of images representing an environment. The images may include image data generated by an image capture device. The processors may also be configured to transmit the image data to an image segmentation network configured to segment the images. The processors may also be configured to receive sensor data associated with the environment including sensor data generated by a sensor of a type different than an image capture device. The processors may be configured to associate the sensor data with segmented images to create a training dataset. The processors may be configured to transmit the training dataset to a machine learning network configured to run a sensor data segmentation model, and train the sensor data segmentation model using the training dataset, such that the sensor data segmentation model is configured to segment sensor data.

Systems and methods of processing crowdsourced navigation information for use in autonomous vehicle navigation are disclosed. A method may include processing, by a mapping server, crowdsourced navigation information from a plurality of vehicles obtained by sensors coupled to the plurality of vehicles, wherein the navigation information describes road lanes of a road segment; collecting data about landmarks identified proximate to the road segment, the landmarking including a traffic sign; generating, by the mapping server, an autonomous vehicle map for the road segment, wherein the autonomous vehicle map includes a spline corresponding to a lane in the road segment and the landmarks identified proximate to the road segment; and distributing, by the mapping server, the autonomous vehicle map to an autonomous vehicle for use in autonomous navigation over the road segment.

A vehicle control device includes: a first detection unit that detects a traveling state of a host vehicle; a merging detection unit that detects that the host vehicle approaches within a predetermined area of a merging point when the host vehicle travels on the merging road toward the merging point at which a main road joins with the merging road; a second detection unit that detects a speed of a lane flow by another vehicle that travels on the main road toward the merging point; a position detection unit that obtains a position of a pre-merging point as a virtual point on the main road reaching the merging point when the host vehicle reaches the merging point; and a display control unit that controls a display device to display the position of the host vehicle and the pre-merging point.

Embodiments facilitate the calibration of cameras in a live action scene using fixed cameras and drones. In some embodiments, a method configures a plurality of reference cameras to observe at least three known reference points located in the live action scene and to observe one or more reference points associated with one or more moving cameras having unconstrained motion. The method further configures the one or more moving cameras to observe one or more moving objects in the live action scene. The method further receives reference point data in association with one or more reference cameras of the plurality of reference cameras, where the reference point data is based on the at least three known reference points and the one or more reference points associated with the one or more moving cameras. The method further computes a location and an orientation of each moving camera of the one or more moving cameras based on one or more of the reference point data and one or more locations of one or more reference cameras of the plurality of reference cameras.

Autonomous ground vehicles capture images during operation, and process the images to recognize ground surfaces or features within their vicinity, such as by providing the images to a segmentation network trained to recognize the ground surfaces or features. Semantic maps of the ground surfaces or features are generated from the processed images. A point on a semantic map is selected, and the autonomous ground vehicle is instructed to travel to a location corresponding to the selected point. The point is selected in accordance with one or more goals, such as to maintain the autonomous ground vehicle at a selected distance from a roadway or other hazardous surface, or along a centerline of a sidewalk.

A system for 3D surveying of an environment by an unmanned ground vehicle (UGV) and an unmanned aerial vehicle (UAV) has two lidar devices. A reference unit has a first and a second marker in a spatially fixed arrangement. An automatic detection of the first marker is carried out for a coordinative measurement by the first lidar device to determine relative position data for providing relative position information of the first marker with respect to the first lidar device. The relative position data and spatial 3D information is used for an automatic detection and a coordinative measurement of the second marker by the second lidar device. The coordinative measurements are used for a referencing of lidar data of the UGV lidar device and lidar data of the UAV lidar device with respect to a common coordinate system.

A method of integrity monitoring for visual odometry comprises capturing a first image at a first time epoch with stereo vision sensors, capturing a second image at a second time epoch, and extracting features from the images. A temporal feature matching process is performed to match the extracted features, using a feature mismatching limiting discriminator. A range, or depth, recovery process is performed to provide stereo feature matching between two images taken by the stereo vision sensors at the same time epoch, using a range error limiting discriminator. An outlier rejection process is performed using a modified RANSAC technique to limit feature moving events. Feature error magnitude and fault probabilities are characterized using overbounding Gaussian models. A state vector estimation process with integrity check is performed using solution separation to determine changes in rotation and translation between images, determine error statistics, detect faults, and compute protection level or integrity risk.