A New Approach on Simultaneous Occupancy Grid Mapping and Particle-based Road Boundary Mapping for Autonomous Vehicles

This paper describes a method of environment mapping for autonomous vehicles that takes the advantages of the high-definition dense local map and sparse global map at the same time. The proposed system consists of two estimators, occupancy grid map estimator that is suitable for online local navigation and the new sparse road boundary map estimator for long-term global mapping. The occupancy grid map is estimated with a common Bayesian inference method. On the other hand, the road boundary map estimator is built based on a simple particle filter algorithm which, compared to grid-based map, is memory efficient as it does not require the algorithm to maintain the occupancy state of each point in space. Both estimations are performed by fusing the information from both LiDAR and camera sensors. Our tests in Carla Simulator have shown that the proposed global road boundary mapping system can construct the global map of the test environment well. The particle filter in the proposed algorithm can also reduce the error of road boundary estimation. Moreover, this paper provides the method to fuse the road boundary map into the grid map, which can improve the accuracy of the grid mapping.