无需专家数据，用并行采样实现机器人轨迹高效规划。
PegasusFlow: Parallel Rolling-Denoising Score Sampling for Robot Diffusion Planner Flow Matching
- 通过分层滚动去噪框架直接从环境交互中采样梯度。
- 复杂障碍穿越任务成功率达100%，比次优方法快18%。
- 适合数据稀缺的专用机器人，尤其擅长复杂地形规划。
扩散模型在机器人轨迹规划中展现出强大生成能力，但其实际部署受限于对专家示范数据的依赖。该范式在数据稀缺的专用机器人场景中不切实际，且训练流程效率低、理论性能不佳。为此，我们提出PegasusFlow，一种分层滚动去噪框架，可直接并行地从环境交互中采样轨迹梯度，完全绕过专家数据需求。核心创新是新型采样算法加权基函数优化（WBFO），利用样条基表示实现更优采样效率与更快收敛，优于传统方法如MPPI。框架嵌入可扩展的异步并行仿真架构，支持大规模并行采样以高效收集数据。在轨迹优化与机器人导航任务中的大量实验表明，尤其是结合强化学习预热的行动价值WBFO（AVWBFO）方法，显著超越基线。在挑战性障碍穿越任务中，本方法成功率100%，比次优方法快18%，验证了其在复杂地形运动规划中的有效性。
原文摘要 · Abstract (English)
Diffusion models offer powerful generative capabilities for robot trajectory planning, yet their practical deployment on robots is hindered by a critical bottleneck: a reliance on imitation learning from expert demonstrations. This paradigm is often impractical for specialized robots where data is scarce and creates an inefficient, theoretically suboptimal training pipeline. To overcome this, we introduce PegasusFlow, a hierarchical rolling-denoising framework that enables direct and parallel sampling of trajectory score gradients from environmental interaction, completely bypassing the need for expert data. Our core innovation is a novel sampling algorithm, Weighted Basis Function Optimization (WBFO), which leverages spline basis representations to achieve superior sample efficiency and faster convergence compared to traditional methods like MPPI. The framework is embedded within a scalable, asynchronous parallel simulation architecture that supports massively parallel rollouts for efficient data collection. Extensive experiments on trajectory optimization and robotic navigation tasks demonstrate that our approach, particularly Action-Value WBFO (AVWBFO) combined with a reinforcement learning warm-start, significantly outperforms baselines. In a challenging barrier-crossing task, our method achieved a 100% success rate and was 18% faster than the next-best method, validating its effectiveness for complex terrain locomotion planning. https://masteryip.github.io/pegasusflow.github.io/
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。