Cai, Zijian (Politecnico di Milano), Sumathy, Vidya (Lulea University of Technology), Calzolari, Gabriele (Luleå University of Technology), Nikolakopoulos, George (Luleå University of Technology)

A Hierarchical Approach for Autonomous Robotic Exploration with Frontier Search and DRL-Based Path Planner

Scheduled for presentation during the Regular Session "Robot Task Planning" (FrAT2), Friday, July 18, 2025, 10:40−11:00, Room 106

Joint 10th IFAC Symposium on Mechatronic Systems and 14th Symposium on Robotics, July 15-18, 2025, Paris, France

This information is tentative and subject to change. Compiled on August 2, 2025

Abstract

Active Simultaneous Localization and Mapping (SLAM) has significantly enhanced the autonomy of robotic systems in real-time exploration, but there remains a constant pursuit for more adaptive and intelligent decision-making capabilities. This paper presents a hierarchical method for autonomous robotic navigation and mapping leveraging frontier-based exploration and Deep Reinforcement Learning (DRL). The high-level frontier searching strategy provides waypoints for a low-level DRL-based path planner, enabling efficient and adaptive navigation in unknown environments. In the proposed methodology, once the robot reaches a desired waypoint, the high-level planner utilizes the current occupancy map created from mapping functions to identify the frontier with the highest entropy. This frontier is then set as the goal for the low-level policy, which is trained using deep reinforcement learning to generate a path to the goal while avoiding obstacles. Our approach has been implemented and evaluated using simulation environments in Gazebo and with real-time experiments. The results demonstrate that the hierarchical approach significantly enhances exploration decision-making capabilities.