Autonomous exploration in unknown, unstructured environments is critical for unmanned ground vehicles (UGVs) in applications like disaster rescue. While search-based methods are suitable for such settings, they often struggle with balancing nonholonomic constraints, exploration efficiency, and mission-specific goals such as target detection and return. This paper introduces a search-based path planning algorithm that addresses these challenges through multi-heuristic fusion and integrated real-time perception. Our approach features three key innovations: (1) a frontier point evaluation function that fuses information gain with Reeds-Shepp curve cost to ensure kinematic feasibility; (2) a multi-heuristic search strategy adopting a minimum-cost priority rule, which dynamically combines wavefront distance (for obstacle avoidance) and RS curve length (for kinematic constraints), incorporating a conflict-resolution mechanism to escape local minima; and (3) a closed-loop "detection-replanning-return" framework, where a YOLOv5s-based visual detector triggers a safe return upon target identification, leveraging LiDAR, GNSS, and IMU data. Extensive validation in simulation (ROS/V-REP) and real-world off-road scenarios (100×500 m) demonstrates the algorithm's robustness and efficiency. It reduces the number of expanded nodes to only 1.38% of a baseline method, with an average planning time of 99 ms. Real-vehicle tests achieved a personnel localization error of 0.327 m and sustained a planning frequency of 12.2-17.2 Hz, demonstrating superior reliability in complex navigation tasks. This work provides a comprehensive and practical solution for autonomous exploration and search-and-rescue missions in complex unknown environments.
Wu et al. (Thu,) studied this question.