From the early beginning, the Simultaneous Localization And Mapping (SLAM) problem has been approached using a probabilistic background. A new solution based on the Transferable Belief Model (TBM) framework is proposed in this article. It appears that this representation of knowledge affords numerous advantages over the classic probabilistic ones and leads to particularly good performances (an average of 3.2% translation drift and 0.0040deg/m rotation drift), especially when it comes to crowded environment. By introducing the basic concepts of a Credibilist SLAM, this article aims at proving that the use of this new theoretical context opens a lot of perspectives for the SLAM community.

Locate a vehicle in an urban environment remains a challenge for the autonomous driving community. By fusing information from a LIDAR, a Global Navigation by Satellite System (GNSS) and the vehicle odometry, this article proposes a solution based on evidential grids and a particle filter to map the static environment and simultaneously estimate the position in a global reference at a high rate and without any prior knowledge.

Lidar has become an essential sensor for autonomous driving as it provides reliable depth estimation. Lidar is also the primary sensor used in building 3D maps which can be used even in the case of low-cost systems which do not use Lidar. Computation on Lidar point clouds is intensive as it requires processing of millions of points per second. Additionally there are many subsequent tasks such as clustering, detection, tracking and classification which makes real-time execution challenging. In this paper, we discuss real-time dynamic object detection algorithms which leverages previously mapped Lidar point clouds to reduce processing. The prior 3D maps provide a static background model and we formulate dynamic object detection as a background subtraction problem. Computation and modeling challenges in the mapping and online execution pipeline are described. We propose a rejection cascade architecture to subtract road regions and other 3D regions separately. We implemented an initial version of our proposed algorithm and evaluated the accuracy on CARLA simulator.

No abstract