外观
论文arXiv 2610.1957914 天前
重回正轨：通过世界模型规划实现部署时策略改进
该框架用离线训练的监测与干预及世界模型规划，在LIBERO-Goal和Franka Panda上提升黑盒视觉运动策略部署表现。
Franka FR3原文链接：Back on Track: Deployment-time Policy Improvement via World Model Planning（arXiv 2610.19579 · 发布日期：2026-10-14）
Back on Track: Deployment-time Policy Improvement via World Model Planning
该框架用离线训练的监测与干预及世界模型规划，在LIBERO-Goal和Franka Panda上提升黑盒视觉运动策略部署表现。
核心要点
- 先进视觉运动策略部署时可能失败，且难以自行预测或恢复。
- 方法以少量带标签on-policy轨迹学习liveness值，并结合play数据训练紧凑潜在世界模型。
- 部署时监测任务进展；若检测到进展丧失，则短视规划纠正动作后交还名义策略。
- 在LIBERO-Goal和Franka Panda上，方法显著提升任务成功率并支持实时控制。
验证范围与局限：验证范围为LIBERO-Goal任务套件和Franka Panda机械臂，名义策略包括π0.5与diffusion policy。
英文摘要 (Abstract)
State-of-the-art visuomotor policies are increasingly capable of executing complex tasks, yet can fail during deployment in ways they cannot predict or recover from on their own. Improving their performance and robustness typically requires collecting more data, retraining, or modifying the policy architecture, all of which are time- and resource-intensive in practice. We instead propose an offline-trained monitoring-and-intervention framework that improves a policy during deployment using only black-box query access. From a limited set of labeled on-policy rollouts, we learn a policy-conditioned liveness value that measures the nominal policy's progress toward task completion; we additionally train a compact latent world model using these rollouts together with play data. At deployment, the liveness value continuously monitors execution. When it detects a loss of progress, a short-horizon planner searches the world model for corrective actions using the same value as its planning objective, after which control returns to the nominal policy. We evaluate our method on the LIBERO-Goal task suite and on a Franka Panda manipulator, using the vision-language-action model $π_{0.5}$ and a diffusion policy as nominal policies, and demonstrate significant improvements in task success rates, while supporting real-time control. Additional results and videos are available on the project website (https://policy-improvement-wm.pages.dev/).
作者：Colton Crosby, Hao Wang, Mac Schwager, Somil Bansal
来源
本页事实对应的公开页面，以原文为准。