The invention relates to a method of creating a map of a navigation region of a vehicle, the method comprising: traveling along a path, predefined by a track guidance marking present in the navigation region, with the vehicle; determining distances of the vehicle from objects possibly present in an environment of the path; and creating the map based on the track guidance marking and on the distances. The invention further relates to a method of determining a pose of a vehicle in a navigation region, the method comprising: determining a position of the vehicle relative to a track guidance marking present in the navigation region; determining distances of the vehicle from objects possibly present in an environment of the vehicle; and determining the pose based on the position, on the distances, and on a map. The invention further relates to a corresponding mapping apparatus and to a corresponding localization apparatus.

This disclosure enables various technologies of cooperative positioning, such as when various positions of various distance sensors are unknown or when various distance sensors have limited sensing capabilities.

An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams – or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data – corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data – and ultimately a fused high definition (HD) map – that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.

Embodiments relate to a client-facing application for interacting with a transport service that transports items via unmanned aerial vehicles (UAVs). An example graphic interface may allow a user to order items to specific delivery areas associated with their larger delivery location, and may dynamically provide status updates and other functionality during the process of fulfilling a UAV transport request.

An apparatus including an interface and a processor. The interface may be configured to receive area data and sensor data from a plurality of vehicle sensors. The processor may be configured to extract road characteristics for a location from the area data, predict expected sensor readings at the location for the plurality of sensors based on the road characteristics, calculate dynamic limits for the sensor data in response to the expected sensor readings and determine a plausibility of the sensor data received from the interface when the vehicle reaches the location. The sensor data may be plausible if the sensor data is within the dynamic limits. A confidence level of the sensor data may be adjusted in response to the plausibility of the sensor data.

In one embodiment, a system and method for partitioning a region for point cloud registration of LIDAR poses of an autonomous driving vehicle (ADV) using a regional iterative closest point (ICP) algorithm is disclosed. The method determines the frame pair size of one or more pairs of related LIDAR poses of a region of an HD map to be constructed. If the frame pair size is greater than a threshold, the region is further divided into multiple clusters. The method may perform the ICP algorithm for each cluster. Inside a cluster, the ICP algorithm focuses on a partial subset of the decision variables and assumes the rest of the decision variables are fixed. To construct the HD map, the method may determine if the results of the ICP algorithms from the clusters converge. If the solutions converge, a solution to the point cloud registration for the region is found.

A method of localizing a robot includes receiving odometry information plotting locations of the robot and sensor data of the environment about the robot. The method also includes obtaining a series of odometry information members, each including a respective odometry measurement at a respective time. The method also includes obtaining a series of sensor data members, each including a respective sensor measurement at the respective time. The method also includes, for each sensor data member of the series of sensor data members, (i) determining a localization of the robot at the respective time based on the respective sensor data, and (ii) determining an offset of the localization relative to the odometry measurement at the respective time. The method also includes determining whether a variance of the offsets determined for the localizations exceeds a threshold variance. When the variance among the offsets exceeds the threshold variance, a signal is generated.

The present invention provides a multi-sensor fusion-based Simultaneous Localization And Mapping (SLAM) mapping method and system for a server, comprising: obtaining a plurality of sensor data regarding a surrounding environment of a moving platform, the plurality of sensor data including point cloud data, image data, inertial measurement unit (IMU) data, and global navigation satellite system (GNSS) data; performing hierarchical processing on the plurality of sensor data to generate a plurality of localization information, wherein one sensor data corresponds to one localization information; obtaining target localization information of the moving platform based on the plurality of localization information; generating a high-precision local map based on the target localization information; and performing a closed-loop detection operation to the high-precision local map to obtain a high-precision global map of the moving platform. The present invention mitigates the technical problem in the related art that easy susceptibility to a surrounding environment leads to low precision.

A first map comprising local features and 3D locations of the local features is generated, the local features comprising visible features in a current image and a corresponding set of covisible features. A second map comprising prior features and 3D locations of the prior features may be determined, where each prior feature: was first imaged at a time prior to the first imaging of any of the local features, and lies within a threshold distance of at least one local feature. A first subset comprising previously imaged local features in the first map and a corresponding second subset of the prior features in the second map is determined by comparing the first and second maps, where each local feature in the first subset corresponds to a distinct prior feature in the second subset. A transformation mapping a subset of local features to a subset of prior features is determined.

A method and system for a vehicle control system generates maps utilized for charting a path of a vehicle through an environment. The method performed by the system obtains information indicative of vehicle movement from at least one vehicle system and images including objects within an environment from a camera mounted on the vehicle. The system uses the gathered information and images to create a depth map of the environment. The system also generates an image point cloud map from images taken with a vehicle camera and a radar point cloud map with velocity information from a radar sensor mounted on the vehicle. The depth map and the point cloud maps are fused together and any dynamic objects filtered out from the final map used for operation of the vehicle.