让视觉语言动作模型在关键时刻提前‘做梦’，避免操作失误导致失败。
DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
- 通过关键阶段触发器识别危险时刻，生成多种可能动作并预演未来。
- 在真实和仿真任务中，成功率显著提升，失败率明显下降。
- 适合需要高可靠性操作的机器人场景，如精密装配或医疗手术。
视觉-语言-动作（VLA）模型在细粒度操作中常因微小动作误差迅速导致不可逆失败。由于现有模型主要依赖成功示范训练，缺乏对关键阶段失败的显式感知。为此，我们提出DreamAvoid，一种关键阶段测试时梦境生成框架，使VLA模型能够预见并规避失败。我们引入自主边界学习范式，细化对成功与失败之间细微边界的理解。具体包括：(1) 使用梦触发器判断执行是否进入关键阶段；(2) 通过动作提议器从VLA采样多个候选动作片段；(3) 利用联合训练于混合数据（成功、失败及边界案例）的梦评估器，对候选动作进行短时程未来预演、价值评估，并选择最优动作。我们在真实世界操作任务和仿真基准上进行了广泛评估，结果表明DreamAvoid能有效避免失败，显著提升整体任务成功率。代码已开源。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly escalate into irrecoverable failures. Since existing VLA models rely predominantly on successful demonstrations for training, they lack an explicit awareness of failure during these critical phases. To address this, we propose DreamAvoid, a critical-phase test-time dreaming framework that enables VLA models to anticipate and avoid failures. We also introduce an autonomous boundary learning paradigm to refine the system's understanding of the subtle boundary between success and failure. Specifically, we (1) utilize a Dream Trigger to determine whether the execution has entered a critical phase, (2) sample multiple candidate action chunks from the VLA via an Action Proposer, and (3) employ a Dream Evaluator, jointly trained on mixed data (success, failure, and boundary cases), to "dream" the short-horizon futures corresponding to the candidate actions, evaluate their values, and select the optimal action. We conduct extensive evaluations on real-world manipulation tasks and simulation benchmarks. The results demonstrate that DreamAvoid can effectively avoid failures, thereby improving the overall task success rate. Our code is available at https://github.com/XianzheFan/DreamAvoid.
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。