SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts
For robotics researchers, this provides a more efficient and robust way to incorporate human preferences into path planning without complex reward engineering.
This work introduces SPADE, a path planning framework for autonomous mobile robots that uses diffusion-based augmentation to improve generalization and robustness of imitation learning. The method achieves 39.1% lower APE and 33.5% lower FID with 93.8% fewer trainable parameters compared to state-of-the-art.
Path planning is essential for Autonomous Mobile Robots (AMRs). Conventional methods for incorporating human preferences into planning typically rely on either complex reward engineering or hardware-intensive solutions. Recent state-of-the-art frameworks leverage imitation learning to train behavior-specific path planning models from expert demonstrations. However, these approaches face two key limitations: limited generalization to unseen environments and low robustness in demonstration collection. To address these challenges, this work introduces an enhanced framework that focuses on two main contributions: an overhauled annotation tool built on ROS 2, and a novel training strategy that integrates diffusion-based augmentation into baseline behavioral cloning models. A dataset of expert demonstrations is provided and evaluated through ablation studies to assess the robustness of the proposed solution. The enhanced approach outperforms state-of-the-art methods with 39.1% lower Absolute Pose Error (APE) and 33.5% lower Fr'echet Inception Distance (FID) while having 93.8% less trainable parameters. Moreover it attains diffusion-level generalization while preserving the real-time, on-edge properties of state-of-the-art models.