通过自适应组合规律，让机器人在新环境下生成合适行为。
Building Generalization Into Behavior Generation Via Adaptive Compositions of Regularities
- 用可微网络表示环境规律，通过反馈动态组合
- 在99%的新场景中生成正确行为，仅1例因规律不足失败
- 自动选择有信息量的规律，适合强化学习与机器人研究者
机器人泛化需要对世界结构的先验知识，但结构会随情境变化。本文提出，泛化源于自适应地将机器人-环境系统中的可预测关系（规律）组合成适用于当前情境的行为生成结构。我们通过分析AICON（Active InterCONnect）框架验证该观点：将规律建模为可微网络中的交互过程，感知反馈实现组合，梯度下降生成行为。在可完全识别所有规律的简化模拟任务中，模型面对大量设计时未考虑的新条件，仍能在99%情况下生成符合上下文的行为，仅1例因编码的规律不足而失败。消融实验表明，网络能根据规律的信息量自动调节其对行为的影响。结果说明，规律的自适应组合是一种强大的归纳偏置，可用于提升行为生成的泛化能力。
原文摘要 · Abstract (English)
Generalization in robotics requires prior knowledge about how the world is structured, yet this structure changes from one situation to the next. This paper investigates the proposition that generalization arises from adaptively composing regularities -- predictable relationships within the robot-environment system -- into situation-appropriate structures for behavior generation. We examine this proposition by analyzing the mechanism in AICON (Active InterCONnect), a framework representing regularities as interacting processes in a differentiable network, where sensory feedback realizes composition and gradient descent generates behavior. To isolate adaptive composition as the key mechanism, we study a simple simulated problem in which all relevant regularities can be identified. We expose the resulting model to a wide range of novel conditions not considered during design, and we find that it generates context-appropriate behavior in all but one case, where encoded regularities are provably insufficient. Ablations reveal that the network automatically modulates which regularities influence behavior based on their informativeness. These results suggest that adaptive composition of regularities constitutes a powerful inductive bias for building generalization into behavior generation.
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。