arXiv:2608.02395cs.RO2026-08

通过内部物理扰动训练机器集体,提升其应对新环境的韧性。

Environmental resilience via morphological diversity within machines

论文配图:Environmental resilience via morphological diversity within machines
图 1 · 摘自论文原文
  • 用可连接部件让多个独立机器在耦合中学习恢复行为。
  • 耦合后系统能承受新环境干扰,无需额外学习即可正常运作。
  • 增加机器数量或多样性可进一步增强集体抗逆能力。

生物体在不同尺度上拥有多样化的传感运动部件,并能快速适应新环境;而机器在微观尺度仅由惰性材料构成,难以应对意外。我们提出假设:生物体的‘内含代理’特性可能增强其韧性——经历内部物理困境或可预训练机体以应对外部挑战。该假设尚未被明确提出,且相关机制亦未阐明。本文揭示一种实现机制:当物理连接器在学习恢复被连接的、形态各异的独立代理行为时,会触发并驯化足够多样的扰动,使后续面对新环境时产生的扰动均处于可控范围,从而无需额外学习即可保持集体正常运行。此外,由更多或更异质的代理组成的集体,其对新环境的韧性更强。这表明,不仅应驯化内部扰动,还应主动制造内部物理困境,以预先训练机器系统应对外部挑战。

原文摘要 · Abstract (English)

Organisms contain diverse, sensorimotor parts across size scales and rapidly adapt to new environments, while machines contain only inert materials at smaller scales and struggle with surprise. We hypothesize that this agents-within-agents quality of organisms may aid their resilience: increasing experiences with internal physical adversity may pre-train organisms and machines to handle external adversity, such as encounters with new environments. Not only has this hypothesis not yet been articulated, mechanisms enabling this phenomenon have yet to be proposed. Here we show a mechanism by which this can occur: we found that physical connectors, in learning to restore behavior to previously independent, morphologically diverse agents they disrupted by tethering them together, trigger and tame sufficiently diverse disruptions that later encounters with new environments trigger disruptions that fall within this manageable range, enabling the collective to continue behaving properly without any additional learning or adaptation. Further, we found that building collectives from more agents, or more diverse agents, further increases the collective's resilience to new environments. This suggests that not just taming but intentionally creating internal physical adversity may indeed prepare organisms for external adversity, and could do so for machines, if they were built from smaller machines.

机器韧性自组织多智能体物理学习

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。