Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions
For UAV autonomous navigation, this work provides a method that simultaneously optimizes mission time and ensures formal safety guarantees, addressing a key trade-off in existing RL-based approaches.
This paper integrates Potential Based Reward Shaping with Control Lyapunov and Barrier Functions to enable zero-shot, safe, and time-efficient UAV navigation. The approach achieves significant reduction in mission time and outstanding performance in complex environments without further training.
Autonomous navigation and obstacle avoidance remain a core challenge of modern Unmanned Aerial Vehicles (UAVs). While traditional control methods struggle with the complexity and variability of the environment, reinforcement learning (RL) enables UAVs to learn adaptive behaviors through interaction with the environment. Existing research with RL prioritizes the mission success at the expense of mission time and safety of UAVs. This study integrates Potential Based Reward Shaping (PBRS) with Control Lyapunov Functions (CLF) and Control Barrier Functions (CBF) to simultaneously optimize mission time and ensure formal safety guarantees. An RL model is trained in a generalized simple environment, then used in complex scenarios incorporating a CLF-CBF-QP filter without further training. Experimental results in simulated environments demonstrate a significant reduction in mission time and outstanding performance in complex environment.