Multi-Sensor Fusion and Obstacle Avoidance Algorithms Applied to Autonomous Driving

Engineering notes

Key topics: autonomous driving system, autonomous driving, autonomous vehicle, lidar, sensor fusion, multi-sensor fusion, waymo, tesla, radar. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

This paper mainly discusses about automation. Autonomous driving has been studied and developed for decades, and the technology has got better and better. More and more people in different fields start to employ autonomous driving, such as logistics and take-out. Moreover, most car companies have been investing heavily in and developing their own autonomous driving systems, and many of them have brought something surprising to the market, such as Tesla and Waymo. It is essential for an autonomous vehicle to employ multi-sensor fusion and improve the obstacle avoidance algorithms because autonomous vehicles must detect the surrounding environment very precisely and immediately, while single kind of sensor cannot guarantee perfect recognition under extreme weather conditions. Therefore, an autonomous vehicle has a large demand of the integration of different sensors, including camera, LiDAR, and millimeter- wave radar. Besides, researchers have also been improving A* algorithm, RVO, YOLO, and so on. This paper focuses on basic information of multi- sensor fusion and obstacle avoidance algorithms, including the background, the achievements of research, thee influence, and the practical applications.

Links and sources

• Official / arXiv page

Comments