Push Smarter, Not Harder: Hierarchical RL-Diffusion Policy for Efficient Nonprehensile Manipulation
By: Steven Caro, Stephen L. Smith
Potential Business Impact:
Robots learn to push objects through messes.
Nonprehensile manipulation, such as pushing objects across cluttered environments, presents a challenging control problem due to complex contact dynamics and long-horizon planning requirements. In this work, we propose HeRD, a hierarchical reinforcement learning-diffusion policy that decomposes pushing tasks into two levels: high-level goal selection and low-level trajectory generation. We employ a high-level reinforcement learning (RL) agent to select intermediate spatial goals, and a low-level goal-conditioned diffusion model to generate feasible, efficient trajectories to reach them. This architecture combines the long-term reward maximizing behaviour of RL with the generative capabilities of diffusion models. We evaluate our method in a 2D simulation environment and show that it outperforms the state-of-the-art baseline in success rate, path efficiency, and generalization across multiple environment configurations. Our results suggest that hierarchical control with generative low-level planning is a promising direction for scalable, goal-directed nonprehensile manipulation. Code, documentation, and trained models are available: https://github.com/carosteven/HeRD.
Similar Papers
Dynamic Legged Ball Manipulation on Rugged Terrains with Hierarchical Reinforcement Learning
Robotics
Robot dogs learn to dribble a ball over rough ground.
Hierarchical Reinforcement Learning in Multi-Goal Spatial Navigation with Autonomous Mobile Robots
Artificial Intelligence
Robots learn to navigate complex places faster.
Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets
Machine Learning (CS)
Guides many robots to herd moving things.