A transferable belief model applied to LIDAR perception for autonomous vehicles

Abstract

Light Detection and Ranging (LIDAR) sensors are commonly used in perception for autonomous vehicles because of their high accuracy, speed, and range. These characteristics make the sensor suitable for integration into the perception layer of controllers which have the capacity to avoid collisions with unpredicted obstacles. The objective of this work was to design a robust and efficient algorithm to acquire useful knowledge from LIDAR scans, and to test its performance in real road situations. The method is based on the construction of an Occupancy Grid based on the Transferable Belief Model, which has proved promising in other studies. Two clear advantages of this method are the reduction of the problem complexity in the phases of segmentation, occlusion detection and tracking, and its ease of integration with other sensors to allow the overall system to evolve towards reliable and complete perception.

Real-Time Motion Tracking for Indoor Moving Sphere Objects with a LiDAR Sensor

“…LiDAR sensors are commonly used in perception for autonomous vehicles because of their high accuracy, speed, and range. These characteristics make the sensors suitable for integration into the perception layer of controllers which have the capacity to avoid collisions with unpredicted obstacles [ 2 ]. LiDAR technology is also applied to field Autonomous Land Vehicles (ALVs) to detect potential obstacles.…”

Longitudinal collision mitigation via coordinated braking of multiple vehicles using model predictive control

“…Hence, longitudinal collision warning and avoidance has the potential to avoid or mitigate a large number of collisions, making this a long-standing topic. Many recent studies have focused on different approaches to improve the traffic safety, for instance, accident detection [1,2,[13][14][15][16]21,31,32], accident analysis and prevention [22,41,42], and R&D of driver assistance systems and autonomous vehicles [7][8][9]27,29,36]. Ngoduy et al built a multi-anticipative macroscopic traffic model to illustrate the influences between vehicles and the importance of a collision system for enhancing traffic safety [29].…”

“…A comprehensive review of collision avoidance systems can be found in [36]. However, most previous research on collision avoidance [7,36] and road safety simulation [41] considered only the nearest two vehicles. This is because the collision avoidance systems were primarily based on on-board sensors (e.g., radar and/or lidar), without inter-vehicle communica-tions.…”

Effect of Pulse‐and‐Glide Strategy on Traffic Flow for a Platoon of Mixed Automated and Manually Driven Vehicles

“…This concept has also resulted in the changes in driver education, fuel‐gauge feedback, and eco‐behavior monitoring. Recent progress on vehicle automation also presents new opportunities to implement eco‐driving technologies (Dharia and Adeli, ; Domínguez et al., ).…”