外观
论文arXiv 2610.0609023 天前
用于生成式机器人策略中一致异步重规划的执行对齐渐进噪声
原文链接：Execution-Aligned Progressive Noise for Consistent Asynchronous Replanning in Generative Robot Policies（arXiv 2610.06090 · 发布日期：2026-10-05）
Execution-Aligned Progressive Noise for Consistent Asynchronous Replanning in Generative Robot Policies
针对异步重规划中动作块续接不一致问题，EAPN通过执行对齐噪声建模，在仿真基准和真实操作任务上验证。
核心要点
- 连续异步重规划需要实时生成动作，但独立随机初始化会导致模式切换和续接不一致。
- EAPN在重规划间传播共享噪声轨迹，并按实际执行位移对齐以建立块间相关性。
- 其在动作块内建模时间相关性，并结合已提交动作上下文来条件化后续生成。
- 结果显示D3IL一致性改善，Kinetix成功率88.59%，LIBERO长延迟下仍保持稳健。
验证范围与局限：验证范围为D3IL、Kinetix、LIBERO及真实Object Storage和双臂Cloth Folding操作任务。
英文摘要 (Abstract)
Continuous asynchronous replanning is essential for real-time generative robot policies, but independent stochastic initialization can cause mode switching and inconsistent continuation across action chunks. We propose Execution-Aligned Progressive Noise (EAPN), which introduces structured stochasticity at both inter-chunk and intra-chunk levels. Across replanning steps, EAPN propagates a shared noise trajectory and aligns it with the actual execution displacement, establishing execution-aligned inter-chunk correlation. Within each action chunk, it models temporal correlation along action time. The aligned stochastic history is further combined with committed action context to condition subsequent generation, allowing new chunks to continue from execution-consistent generative states rather than restart from independent noise. We evaluate EAPN on D3IL, Kinetix, LIBERO, and real-world manipulation tasks. EAPN improves multimodal behavior consistency on D3IL and achieves an average success rate of 88.59% on Kinetix. On LIBERO, it remains robust and maintains strong task performance even under long inference delays. Real-robot experiments further achieve 90.0% success on Object Storage and 96.7% on bimanual Cloth Folding, demonstrating reliable continuous execution under asynchronous replanning.
作者：Di Wu, Ping Liu, Xuhua Chen, He Zheng, Lingfeng Zhang, Tao Zhang
来源
本页事实对应的公开页面，以原文为准。