| CPC G06T 7/73 (2017.01) [G05D 1/2465 (2024.01); G05D 1/242 (2024.01); G05D 2111/14 (2024.01); G06T 2207/10028 (2013.01); G06T 2207/20021 (2013.01)] | 14 Claims |
|
1. A computer-implemented method for determining an ego pose of a mobile system and creating a surfel map, based on 3D ellipsoids, of a surrounding area by means of an optimization problem represented by a factor graph, comprising the steps of:
receiving environment sensor data, wherein the environment sensor data have been generated by at least one environment sensor that is attached to the mobile system and surveys the area surrounding the mobile system, and wherein the environment sensor data represent the area surrounding the mobile system as a point cloud, in each case in a specific time period,
generating surfels by converting the point cloud of the received environment sensor data into surfel data,
identifying new surfels and known surfels in the generated surfels by comparing the surfel data with the surfel map, and
adding a surfel factor for the surfels identified as known surfels to the factor graph and/or adding a surfel node and a surfel factor for surfels identified as new surfels to the factor graph,
wherein a node of the factor graph represents a specific ego pose of the mobile system or, when in the form of a surfel node, a specific surfel in map coordinates,
wherein an edge between a node that represents an ego pose and a node that represents a surfel represents, as a surfel factor, a spatial restriction between the ego pose represented by the node and the surfel that is identifiable for the environment sensor from the specific ego pose, and includes a probability distribution in relation to the representability of that surfel for the environment sensor from the specific ego pose, and
wherein the factor graph representing the optimization problem is incrementally created after the environment sensor data of a first specific time period are received, and the optimization problem is incrementally solved before the surfel factors of the surfels identified as known surfels, and/or before the surfel nodes and surfel factors of the new surfels are added to the factor graph, and the steps are repeated for environment sensor data of a later specific time period than the first specific time period.
|