外观
论文arXiv 2610.1914113 天前
PACE框架解耦任务意图与动力学，跨具身操作零样本成功率达89%
本文由 AI 根据公开内容整理，可能有误，请以原文为准：Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation（arXiv 2610.19141）
核心内容
针对多机器人集体学习中因本体动力学差异导致的策略模糊与性能崩溃问题，研究提出PACE两阶段学习框架。该方法在仿真环境中实现超过93%的整体操作成功率，在动态分布外（OOD）零样本机器人上达到89%成功率，大幅超越Transformer行为克隆（82%）和Diffusion Policy（66%）基线，并成功完成KUKA机械臂的物理部署验证。
技术架构包含基于离线轨迹预训练的表征层以提取共享任务上下文，以及配备预测性动力学适配器的决策层。该适配器强制潜在状态预测未来转移，作为隐式正则化项将策略锚定于执行本体的特定动力学，同时保持实时推理无需在线规划。这种解耦设计有效解决了不同具身对同一笛卡尔指令响应不一致的问题，确保了跨平台泛化能力。
关键看点
- 跨具身性能：仿真整体成功率超93%，动态分布外零样本机器人达89%，优于Diffusion Policy基线23个百分点
- 核心机制：引入预测性动力学适配器作为隐式正则化，解耦共享任务意图与本体相关转移特性
- 推理效率：决策层支持实时推理且无需在线规划，满足物理部署的低延迟控制需求
- 真机验证：在KUKA机械臂上完成全状态流水线零样本Sim-to-Real迁移，验证工程落地可行性
工程与产业观察
PACE通过解耦任务语义与本体动力学，为异构机器人集群提供了高效的统一操作策略学习范式。其预测性适配器机制在不增加推理开销的前提下解决了跨具身泛化难题，对构建通用具身智能基础模型及降低多机型适配成本具有重要参考价值，尤其适用于工业场景下多品牌机械臂的统一技能复用。
英文摘要 (Abstract)
Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodiment-dependent transition dynamics. Collective learning aggregates multi-robot experience to discover shared task structure, yet naive aggregation can average incompatible action modes when different embodiments realize the same Cartesian command through different transition behavior. This leads to strategy ambiguity and performance collapse on dynamically outlying embodiments. To address this, we propose PACE, a two-stage collective learning framework that separates shared task-space intent from embodiment-dependent transition dynamics. The first stage employs a representation layer pre-trained on offline trajectories to extract task-level context from collective data. The second stage introduces a decision layer equipped with a predictive dynamics adapter. By forcing the latent state to predict future transitions, this adapter acts as a latent regularizer that grounds the policy in the transition behavior of the executing robot while preserving real-time inference without online planning. Evaluations across simulated embodiments demonstrate that our method prevents performance collapse on distinct robots. It achieves over 93% overall success and 89% on dynamically out-of-distribution zero-shot simulated robots, outperforming the Transformer behavior cloning (82%) and diffusion policy baselines (66%). Physical KUKA deployment further validates the feasibility of the full state-based pipeline under zero-shot sim-to-real transfer.
作者：Shaocheng Liu, Yuan Meng, Zhenshan Bing, Alois Knoll
来源
本页事实对应的公开页面，以原文为准。