ED-SAC Reinforcement Learning-Based Adaptive Cruise Trajectory Planning Method for UAVs in Grassland Highway Inspection Scenarios

To address the issue of traffic accidents caused by livestock crossing roads on grassland highways, this paper proposes an adaptive cruise control method for unmanned aerial vehicles (UAVs) based on an ensemble Q-network and a Soft Actor-Critic (SAC) with delayed policy updates, namely the ED-SAC algorithm. Building upon the standard SAC framework, this method introduces multiple independent Critic networks to form an ensemble Q-network, and employs a random subset minimization strategy during the calculation of target Q-values to mitigate policy bias resulting from overestimated values; simultaneously, a delayed policy update mechanism decouples the optimization processes of the Actor and Critic networks, thereby enhancing training stability and control robustness. Using the PyBullet simulation platform, this paper constructs a UAV inspection scenario on grassland roads and designs three typical test tasks: infinite loop, grid scan and spiral trajectories, to conduct comparative validation of the PPO, TD3, SAC and ED-SAC algorithms. Experimental results demonstrate that, under disturbance-free conditions, ED-SAC achieves the highest mission success rate and the lowest tracking error across all three trajectory scenarios, with an average tracking error as low as 0.27 m and a mission success rate as high as 98.7%. Under continuous random external disturbances, ED-SAC still maintains high trajectory tracking accuracy and attitude control stability, with a mission success rate reaching up to 96.2%. The results demonstrate that the proposed ED-SAC algorithm can effectively enhance the trajectory tracking accuracy, training stability and anti-disturbance capability of UAVs in complex grassland road inspection scenarios, providing a reliable intelligent control method for active grassland road inspection and traffic safety early warning.