Adversarial Geometric Traps: A DRL-Driven ROS 2 Framework for Robust Mapless Navigation in Dead-End Scenarios
Reactive local planners such as the Dynamic Window Approach (DWA) often fail in non-convex dead-end structures because their greedy objective drives the robot into local minima. This paper presents a ROS 2-native mapless navigation framework that trains a Proximal Policy Optimization (PPO) agent using a Procedural Adversarial Trap Generator (ATG) in Gazebo. The generator systematically produces U-shaped traps, corners, and narrow passages so that the agent learns proactive avoidance and recovery behavior rather than merely reacting to nearby obstacles. In simulation, the proposed DRL policy achieves an 88% success rate in complex maze scenarios, while the DWA baseline drops to 8%. A zero-shot deployment on a physical Unitree Go2 further confirms that the learned behavior transfers to real hardware despite LiDAR noise and odometry uncertainty.