外观
论文arXiv 2611.02462今天
Dogger四足机器人形态控制协同设计降低运输成本35.7%
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Learning Purposeful Co-designs of Bio-inspired Quadrupedal Robots(arXiv 2611.02462)
核心内容
针对四足机器人形态与控制分离设计导致效率受限的问题,研究团队推出仿生四足机器人Dogger及其配套的两阶段协同设计框架。该系统采用模块化三节腿结构、四连杆机构及可调被动膝关节顺应性,显著扩展了物理设计空间。实验数据显示,相比传统固定或受限设计方案,全几何-顺应性协同设计在检测与负载搬运任务中实现零样本部署,运输成本(Cost of Transport)分别降低18.6%和35.7%,验证了扩大物理设计空间对任务驱动型形态-控制协同优化的关键作用。
技术架构上,Dogger采用强化学习与贝叶斯优化结合的两阶段框架:首先训练跨设计的形态条件化控制策略并保持固定,随后针对特定任务进行设计参数寻优。这种解耦机制使得算法能在统一策略下探索更广阔的机械构型空间。跨任务测试揭示了不同任务导向的差异化形态特征及其共享的机械权衡关系,证明了将学习控制与可扩展硬件设计深度融合,是突破现有腿式机器人性能瓶颈的有效路径,为具身智能硬件迭代提供了量化依据。
关键看点
- 运输成本优化:全几何-顺应性协同设计在检测与负载任务中零样本部署,运输成本分别降低18.6%和35.7%
- 硬件构型创新:Dogger采用模块化三节腿、四连杆机构及可调被动膝关节顺应性,突破传统受限设计空间限制
- 两阶段优化框架:结合强化学习与贝叶斯优化,先训形态条件策略再固定策略寻优,解耦形态与控制设计流程
- 机械权衡发现:跨任务测试揭示不同任务需差异化形态,但存在共享机械权衡,证实扩展物理空间必要性
工程与产业观察
该研究以量化数据证明,仅靠算法优化难以触及腿式机器人性能天花板,必须同步扩展硬件设计空间。其两阶段协同设计框架为具身智能研发提供新范式:在统一控制策略下搜索最优机械构型,避免陷入局部最优。这对人形/四足机器人的关节模组选型、被动柔顺设计及Sim-to-Real迁移具有直接工程参考价值。
英文摘要 (Abstract)
Treating morphology and control as separate design problems has constrained the efficiency and adaptability of quadrupedal robots, while current co-design approaches are often constrained by restricted design spaces. We overcome this limit by introducing Dogger, a bio-inspired quadruped with modular three-segment legs, four-bar linkages and adjustable passive knee compliance. A two-stage framework combining reinforcement learning and Bayesian optimization is developed: the morphology-conditioned control policy is trained across designs and then held fixed during task-specific design selection. The resulting designs and policies deployed zero-shot reduce the cost of transport by 18.6% and 35.7% for inspection and payload-carrying tasks. Comparisons demonstrate that full geometry-compliance co-design outperforms fixed and restricted design scopes. Cross-task tests further reveal distinct task-specific morphologies with shared mechanical trade-offs. These results provide hardware-level evidence that expanding the physical design space alongside learned control is essential to realize the full potential of task-driven morphology-control co-design in legged robotics.
作者:Fabio Boekel, Jiatao Ding, Cosimo Della Santina
来源
本页事实对应的公开页面,以原文为准。