Obstacle detection and avoidance system based on layered costmaps for robot tractors

In the context of automated navigation for agricultural vehicles, efficient obstacle avoidance remains a significant challenge, particularly on farm roads where road conditions vary. This paper presents a novel obstacle detection and avoidance system based on layered costmaps, designed to enhance the safety and efficiency of robot tractors navigating farm roads. The system integrates a cost-effective 2D LiDAR sensor for obstacle detection, combined with real-time avoidance maneuver calculation to ensure continuous and safe operation. A static layer map was created using a simple image processing technique, so it can be easily integrated with the layered costmaps. The system’s performance was validated through three experimental setups. For single obstacle avoidance, the system achieved an RMSE of 0.15 m in lateral avoidance distance. For two parallel obstacles, the RMSE was 0.19 m, and for two consecutively aligned obstacles, the RMSE was below 0.28 m. These results demonstrate the effectiveness of the proposed system in ensuring stable obstacle detection and avoidance, highlighting its potential for practical use in agricultural machinery for field operations. The method provides a cost-efficient solution, bypassing the need for complex sensor fusion and synchronization, making it highly suitable for real-world deployment.