Abstract: The present application discloses a positioning method and an apparatus, which relate to the technical field of intelligent driving. A specific implementation solution is: determining a first positioning result using point cloud data collected by lidar in combination with a laser point cloud reflection value map; constructing a constraint condition using the first positioning result, where the constraint condition is used to accelerate a convergence speed of solving a receiver position using observation data; performing GNSS-PPP positioning using the constraint condition in combination with observation data of a GNSS receiver to obtain a second positioning result. Using this solution, lidar positioning technology is combined with GNSS-PPP positioning technology to realize a purpose of not relying on a GNSS base station.

Abstract: Embodiments of the present disclosure provide a positioning method, a positioning apparatus, a vehicle device, an autonomous vehicle and a storage medium, which relate to the field of automatic driving technology, where the method includes: acquiring navigation information respectively output by at least two Kalman filters, where each of the Kalman filters is connected to an inertial measurement unit, and fusing the multiple pieces of navigation information to obtain positioning information. By connecting one inertial measurement unit to one Kalman filter and fusing multiple pieces of navigation information acquired from the respective Kalman filters, it is possible to avoid low efficiency and huge calculations when one Kalman filter is used to calculate relevant information output by multiple inertial measurement units, and reduce the amount of calculations of the respective Kalman filters and improve calculation efficiency.

Abstract: A positioning method includes acquiring an image of an area where a target object is located at a first time instant and multiple frames of point cloud data of an area where the target object is located at multiple time instants, wherein the multiple frames of point cloud data include first point cloud data of the area where the target object is located at the first time instant. The method also includes determining a point cloud map according to the multiple frames of point cloud data and acquiring a target feature vector according to the first point cloud data, the point cloud map and the image. The method further includes determining a positioning result of the target object according to the target feature vector.

Abstract: The disclosure provides a method, an apparatus, a device and a storage medium for positioning an object. The method includes: obtaining a map related to a region where the object is located, the map including a plurality of map layers having different height information; determining, based on the map and current point cloud data related to the object, an estimated position of the object, an estimated height corresponding to the estimated position and an estimated probability that the object is located at the estimated position with an estimated posture; and determining, at least based on the estimated position, the estimated height and the estimated probability, positioning information for the object, the positioning information indicating at least one of a current position of the object, a current height of the object and a current posture of the object.

Abstract: 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.

Abstract: In one embodiment, a system and method for point cloud registration of LIDAR poses of an autonomous driving vehicle (ADV) is disclosed. The method selects poses of the point clouds that possess higher confidence level during the data capture phase as fixed anchor poses. The fixed anchor points are used to estimate and optimize the poses of non-anchor poses during point cloud registration. The method may partition the points clouds into blocks to perform the ICP algorithm for each block in parallel by minimizing the cost function of the bundle adjustment equation updated with a regularity term. The regularity term may measure the difference between current estimates of the poses and previous or the initial estimates. The method may also minimize the bundle adjustment equation updated with a regularity term when solving the pose graph problem to merge the optimized poses from the blocks to make connections between the blocks.

Abstract: The present disclosure discloses a method and apparatus for positioning a vehicle. In some embodiments, the method comprises: acquiring an a priori position of a to-be-positioned vehicle at a current positioning moment determined by performing a strapdown calculation between a previous positioning moment and the current positioning moment; determining a map area for searching in a laser point cloud reflected value map; matching a reflected value characteristic of a projection area generated by projecting a real-time laser point cloud, to obtain a map matching position according to a matching result; positioning, using the a priori position in combination with observation data of a vehicle-mounted global navigation satellite system (GNSS) receiver of the vehicle, to obtain a satellite positioning position; and fusing the a priori position, the map matching position and the satellite positioning position to generate a positioning result of positioning the vehicle at the current moment.

Abstract: The present disclosure provides a method and a device for positioning, an apparatus and a computer readable storage medium. The method includes acquiring a visual feature map of a geographic area located by a movable object. The visual feature map includes a first set of visual features. The method further includes acquiring at least one image captured by a camera coupled to the movable object during a motion of the movable object within the geographic area. The method further includes extracting a second set of visual features corresponding to the first set of visual features from the at least one image. In addition, the method further includes determining at least one pose of the movable object during the motion at least based on the visual feature map and the second set of visual features.

Abstract: Embodiments of the present disclosure provide a method and apparatus for evaluating data, a device, and a computer-readable storage medium in the field of autonomous driving. The method may include: generating, at least based on satellite navigation data related to a vehicle, a reference position and posture data set of the vehicle; generating, at least based on a part of the satellite navigation data, a test position and posture data set of the vehicle, the accuracy of the test position and posture data set being lower than that of the reference position and posture data set; obtaining a revised position and posture data set for the test position and posture data set; and evaluating, based on the reference position and posture data set and the revised position and posture data set, a correction performance for the test position and posture data set.

Abstract: The embodiments provide a method for unmanned vehicle cruising, an unmanned vehicle and a storage medium, the method includes: in a state that a slow cruising function is started, cruising according to a preset cruising mode, and collecting running data through a sensing device, where the running data is data of an environment in which a vehicle locates, collected by the vehicle during a running process; and generating a map based on the collected running data. The embodiments of the present disclosure solve the problem that an unmanned vehicle in the prior art cannot update a map in time and, in particular, cannot develop a more suitable map according to different surrounding environments.

Abstract: Embodiments of the present disclosure provide a method and a device for generating an electronic map, an electronic device, a computer readable storage medium, and an acquisition entity. The method includes: obtaining a first point cloud sequence and a second point cloud sequence for a preset region; generating a first grid map for the first point cloud sequence and a second grid map for the second point cloud sequence, wherein a grid in each of the first grid map and the second grid map at least comprises reflection value information of a point cloud; and optimizing the first point cloud sequence based on the first grid map and the second grid map.

Abstract: In one embodiment, a system uses an actor-critic reinforcement learning model to generate a trajectory for an autonomous driving vehicle (ADV) in an open space. The system perceives an environment surrounding an ADV. The system applies a RL algorithm to an initial state of a planning trajectory based on the perceived environment to determine a plurality of controls for the ADV to advance to a plurality of trajectory states based on map and vehicle control information for the ADV. The system determines a reward prediction by the RL algorithm for each of the plurality of controls in view of a target destination state. The system generates a first trajectory from the trajectory states by maximizing the reward predictions to control the ADV autonomously according to the first trajectory.

Abstract: In one embodiment, an open space model is generated for a system to plan trajectories for an ADV in an open space. The system perceives an environment surrounding an ADV including one or more obstacles. The system determines a target function for the open space model based on constraints for the one or more obstacles and map information. The system iteratively, performs a first quadratic programming (QP) optimization on the target function based on a first trajectory while fixing a first set of variables, and performs a second QP optimization on the target function based on a result of the first QP optimization while fixing a second set of variables. The system generates a second trajectory based on results of the first and the second QP optimizations to control the ADV autonomously according to the second trajectory.

Abstract: In one embodiment, a system generates a plurality of driving scenarios to train a reinforcement learning (RL) agent and replays each of the driving scenarios to train the RL agent by: applying a RL algorithm to an initial state of a driving scenario to determine a number of control actions from a number of discretized control/action options for the ADV to advance to a number of trajectory states which are based on a number of discretized trajectory state options, determining a reward prediction by the RL algorithm for each of the controls/actions, determining a judgment score for the trajectory states, and updating the RL agent based on the judgment score.

Abstract: In a specific implementation of the method a reflectance map is constructed based on a position and an Euler angle, obtained through a global optimization and used for constructing a reflectance map, of a center of a laser radar corresponding to each frame laser point cloud used for constructing the reflectance map collected in each collection region. This implementation implements the level-by-level pose optimization of laser point clouds used for constructing a reflectance map that are collected in each collection region in an excessively large region, to obtain an accurate position and Euler angle, used for constructing the reflectance map, of a laser radar center corresponding to each frame laser point cloud used for constructing the reflectance map.

Abstract: The present application discloses a method and apparatus for updating a map. An implementation of the method comprises: acquiring a laser point clouds obtained by scanning a surrounding environment and acquiring a periodic pose change of a vehicle in a scanning period; determining an a priori pose of the laser radar at a reference time in the current scanning period based on a known pose of the laser radar in a previous scanning period and the periodic pose change; performing motion compensation on the scanned laser point clouds to form a compensated point cloud frame; generating a partial point cloud characteristic map; matching the partial point cloud characteristic map with a map area obtained in a reference point cloud map, and correcting the a priori pose to obtain an a posteriori pose; and updating a three-dimensional point cloud map of a to-be-constructed area using the compensated point cloud frame.

Abstract: Systems and methods are described for multithreaded navigation assistance by acquired with a single camera on-board a vehicle, using 2D-3D correspondences for continuous pose estimation, and combining the pose estimation with 2D-2D epipolar search to replenish 3D points.

Abstract: The present disclosure provides a laser point cloud positioning method and system. The method comprises: converting laser point cloud reflection value data and height value data matched with a current location of an autonomous vehicle into laser point cloud projection data in a ground plane; assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map; determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map.

Abstract: The present application provides a method for detecting map error information, an apparatus, a device, a vehicle and a storage medium, where the method includes: acquiring current environmental feature information around a vehicle; and detecting, according to the current environmental feature information and map data, whether the map data is erroneous. Whether the map data is erroneous is detected in real time based on the current environmental feature information during the process of the actual traveling of the vehicle, which improves timeliness and efficiency for the map error detection, thereby the map data can be corrected in time and the traveling safety of the vehicle may be improved.

Abstract: The present application provides a self-driving vehicle positioning method, an apparatus and a storage medium, where the method includes: obtaining reference data, where the reference data includes: state information and running path information of at least one traffic participant within a preset distance from a self-driving vehicle, and updating positioning information of the self-driving vehicle according to the reference data. In the technical solutions, when a GPS signal is weak, the self-driving vehicle can also update the positioning information in time, thereby ensuring driving safety of the self-driving vehicle, and solving a driving safety problem existing in the self-driving vehicle of the prior art.