用低质量演示训练扩散模型，让机械臂学会复杂路径规划。
Denoising Diffusion Planner: Learning Complex Paths from Low-Quality Demonstrations
- 用合成和低质演示数据训练扩散模型生成路径
- 无需高质量数据即可实现避障并抵达任意目标
- 结合无分类器与有分类器采样，适合机器人路径规划
去噪扩散概率模型（DDPM）是强大的生成式深度学习模型，在图像生成和近期路径规划与控制中表现优异。本文研究如何利用DDPM的泛化能力和条件采样特性，为机械臂末端执行器生成复杂路径。实验表明，仅使用合成数据和低质量示范训练的DDPM即可生成非平凡路径，实现任意目标到达并避开障碍物。同时，我们对比了结合无分类器与有分类器引导的条件采样策略。最终，将该模型部署于滚动时域控制框架中，进一步提升其规划能力。在Franka Emika Panda机器人上通过多种实验验证了该方法的有效性。
原文摘要 · Abstract (English)
Denoising Diffusion Probabilistic Models (DDPMs) are powerful generative deep learning models that have been very successful at image generation, and, very recently, in path planning and control. In this paper, we investigate how to leverage the generalization and conditional sampling capabilities of DDPMs to generate complex paths for a robotic end effector. We show that training a DDPM with synthetic and low-quality demonstrations is sufficient for generating nontrivial paths reaching arbitrary targets and avoiding obstacles. Additionally, we investigate different strategies for conditional sampling combining classifier-free and classifier-guided approaches. Eventually, we deploy the DDPM in a receding-horizon control scheme to enhance its planning capabilities. The Denoising Diffusion Planner is experimentally validated through various experiments on a Franka Emika Panda robot.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。