通过模拟机械臂学习低层因果关系，提升机器人对环境的可解释理解。
Learning Low-Level Causal Relations using a Simulated Robotic Arm
- 基于仿真机械臂数据训练前后向模型，挖掘动作与状态间的因果关系。
- 通过特征归因分析，定位状态向量中影响结果的关键关节与环境特征。
- 为状态降维和高层因果解释提供可信赖的底层依据，适合机器人可解释性研究者。
因果学习使人类能够预测自身行为对已知环境的影响，并据此规划更复杂的动作。此类知识还能捕捉环境行为模式，用于环境分析与行为推理，对具备常识的智能机器人系统设计至关重要。本文通过模拟机械臂在两项传感运动任务中生成的数据，研究因果关系，学习前向与逆向模型。进一步，探究了前向模型的特征归因方法，揭示状态向量中与机械臂关节及环境特征相关的个体特征所对应的低层因果效应。该分析为状态表示的降维提供了坚实基础，并支持向高层因果解释的知识聚合。
原文摘要 · Abstract (English)
Causal learning allows humans to predict the effect of their actions on the known environment and use this knowledge to plan the execution of more complex actions. Such knowledge also captures the behaviour of the environment and can be used for its analysis and the reasoning behind the behaviour. This type of knowledge is also crucial in the design of intelligent robotic systems with common sense. In this paper, we study causal relations by learning the forward and inverse models based on data generated by a simulated robotic arm involved in two sensorimotor tasks. As a next step, we investigate feature attribution methods for the analysis of the forward model, which reveals the low-level causal effects corresponding to individual features of the state vector related to both the arm joints and the environment features. This type of analysis provides solid ground for dimensionality reduction of the state representations, as well as for the aggregation of knowledge towards the explainability of causal effects at higher levels.
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。