模型

DynaHarness:机器人动态物理约束系统

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

精选理由

清华团队发布DynaHarness,让机器人通过物理约束实现自我进化,成功率提升4倍。

DynaHarness通过共享执行契约将语义推理与物理治理相结合。该系统在LIBERO-Pro基准测试中达到75.

正文

2%成功率,远高于冻结策略的17.5%。

使用相同能力库时,完整动态执行达到74.0%,优于单步重规划的63.

9%。该系统能将失败证据转化为验证过的能力修订。

原文 · arXiv cs.AI

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system component should be revised. We propose DynaHarness, a dynamic physical harness that couples semantic reasoning with physical governance through a shared execution contract and turns failure evidence into validated capability revisions. To be more specific, the slow brain proposes capabilities and symbolic arguments, while the fast brain grounds and monitors commands, refuses unresolved actions, substitutes capabilities, and requests replans when needed. The physical execution contract bounds each accepted command and records execution evidence across analytic skills, recovery skills, and the frozen VLA. Failure attribution localizes faults in these records and directs targeted revisions of reusable capabilities or execution mechanisms. Paired regression checks govern admission or rejection, closing the self-evolution loop. On LIBERO-Pro, DynaHarness achieves 75.2% on 800 newly sampled initial states, compared with 17.5% for the frozen policy. With the same capability library, full dynamic execution reaches 74.0% versus 63.9% under nominal one-step replanning. This demonstrates the value of DynaHarness as a dynamic physical harness that governs how existing capabilities are grounded, monitored, and coordinated during execution. Our project page is at https://denghaoyuan123.github.io/Dynaharness_page/.

产业坐标与信源核验

本条情报归属 AITOP「模型」核心栏目,重点聚焦中国 AI 产业与国产大模型生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:DynaHarness、机器人、LIBERO-Pro、物理约束,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Haoyuan Deng, Jiebin Liu, Tengxiao Zhang, Langning Yan, Hongye Cao, Ziwei Wang),经 AITOP 多维评分管线结构化提炼。截至目前,全网已有 2 家独立信源对该事件进行交叉印证与跟进报道(含 pandaily 等),属于近期高关注度行业信号。