An Efficient Path Planning Algorithm for Autonomous Racing Systems

Autonomous driving (AD) has gained tremendous attention in recent years due to its great potential in enhancing road safety. This rising popularity has led to an emerging research field called autonomous racing. The idea of applying autonomous driving techniques to racing is expected to push the envelope of autonomous technology to its limits due to the requirement of high-speed processing and racing rules such as racing flags. In this paper, we propose a simple yet efficient path-planning algorithm for autonomous racing systems. The algorithm consists of two planners: global and local. The global planner is used to handle different flags in car racing and generate a global path, while the local planner with an adaptive-resolution occupancy grid-based planning method is deployed to avoid obstacles and enhance the safety of high-speed driving. The algorithm is implemented in an autonomous vehicle and tested at the proving ground of the Korea Intelligent Automotive Parts Promotion Institute (KIAPI), under the 2024 autonomous driving competition for university students, Daegu, Republic of Korea.