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 Adve...