Learning Autonomy: Off-Road Navigation Enhanced by Human Input
This addresses the problem of unpredictable off-road navigation for autonomous vehicles, though it appears incremental in applying learning methods to this specific domain.
The paper tackles off-road autonomous navigation by developing a learning-based local planner that captures human driving nuances from minimal demonstration data (5-10 minutes), enabling quick adaptation to various terrains without manual fine-tuning.
In the area of autonomous driving, navigating off-road terrains presents a unique set of challenges, from unpredictable surfaces like grass and dirt to unexpected obstacles such as bushes and puddles. In this work, we present a novel learning-based local planner that addresses these challenges by directly capturing human driving nuances from real-world demonstrations using only a monocular camera. The key features of our planner are its ability to navigate in challenging off-road environments with various terrain types and its fast learning capabilities. By utilizing minimal human demonstration data (5-10 mins), it quickly learns to navigate in a wide array of off-road conditions. The local planner significantly reduces the real world data required to learn human driving preferences. This allows the planner to apply learned behaviors to real-world scenarios without the need for manual fine-tuning, demonstrating quick adjustment and adaptability in off-road autonomous driving technology.