Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States

TL;DR

This paper introduces a cold diffusion approach that leverages the replay buffer of visited states to improve the feasibility and obstacle avoidance of robot plans generated through imitation learning.

Contribution

It applies cold diffusion to guide planning via replay buffer states, enhancing feasibility and obstacle avoidance in robot trajectory generation.

Findings

Significant improvement in obstacle avoidance during planning.

Enhanced likelihood of feasible trajectories occupying the robot's state space.

Effective use of cold diffusion with replay buffer for imitation learning.

Abstract

Learning from demonstrations (LfD) has successfully trained robots to exhibit remarkable generalization capabilities. However, many powerful imitation techniques do not prioritize the feasibility of the robot behaviors they generate. In this work, we explore the feasibility of plans produced by LfD. As in prior work, we employ a temporal diffusion model with fixed start and goal states to facilitate imitation through in-painting. Unlike previous studies, we apply cold diffusion to ensure the optimization process is directed through the agent's replay buffer of previously visited states. This routing approach increases the likelihood that the final trajectories will predominantly occupy the feasible region of the robot's state space. We test this method in simulated robotic environments with obstacles and observe a significant improvement in the agent's ability to avoid these obstacles during planning.