2025/06/02 by Ying Yu, Junhong Xu, Yu, Youwei +2 · 1 citation
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #FOS: Computer and information sciences #FOS: Electrical engineering #Reinforcement Learning in Robotics #Robotic Path Planning Algorithms #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2506.01759
openalex publication_date 2025/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Model-free reinforcement learning has emerged as a powerful method for developing robust robot control policies capable of navigating through complex and unstructured environments. The effectiveness of these methods hinges on two essential elements: (1) the use of massively parallel physics simulations to expedite policy training, and (2) an environment generator tasked with crafting sufficiently challenging yet attainable environments to facilitate continuous policy improvement. Existing methods of outdoor environment generation often rely on heuristics constrained by a set of parameters, limiting the diversity and realism. In this work, we introduce ADEPT, a novel Adaptive Diffusion Environment for Policy Transfer in the zero-shot sim-to-real fashion that leverages Denoising Diffusion Probabilistic Models to dynamically expand existing training environments by adding more diverse and complex environments adaptive to the current policy. ADEPT guides the diffusion model's generation process through initial noise optimization, blending noise-corrupted environments from existing training environments weighted by the policy's performance in each corresponding environment. By manipulating the noise corruption level, ADEPT seamlessly transitions between generating similar environments for policy fine-tuning and novel ones to expand training diversity. To benchmark ADEPT in off-road navigation, we propose a fast and effective multi-layer map representation for wild environment generation. Our experiments show that the policy trained by ADEPT outperforms both procedural generated and natural environments, along with popular navigation methods.