提出因果感知框架，让机器人更懂环境动态关系。
Efficient and Generalizable Environmental Understanding for Visual Navigation
- 引入因果视角，建模历史观测间的内在关联
- 在多种任务与环境中性能超越基线方法
- 无需额外计算成本，适配强化与监督学习
视觉导航是具身智能的核心任务，使智能体能够朝着目标在复杂环境中导航。在各类导航任务中，通常需要对前序时间步积累的序列数据进行建模。现有方法虽表现良好，但通常同时处理所有历史观测，忽视了数据内部的关联结构，可能限制了性能进一步提升。本文通过因果视角分析导航任务特性，揭示传统序列方法的局限性。基于此，提出因果感知导航（CAN），引入因果理解模块以增强智能体的环境理解能力。实验表明，该方法在多种任务和仿真环境中持续优于基线。大量消融实验证实性能提升源于因果理解模块，其在强化学习与监督学习设置下均具备良好泛化能力，且无计算开销增加。
原文摘要 · Abstract (English)
Visual Navigation is a core task in Embodied AI, enabling agents to navigate complex environments toward given objectives. Across diverse settings within Navigation tasks, many necessitate the modelling of sequential data accumulated from preceding time steps. While existing methods perform well, they typically process all historical observations simultaneously, overlooking the internal association structure within the data, which may limit the potential for further improvements in task performance. We address this by examining the unique characteristics of Navigation tasks through the lens of causality, introducing a causal framework to highlight the limitations of conventional sequential methods. Leveraging this insight, we propose Causality-Aware Navigation (CAN), which incorporates a Causal Understanding Module to enhance the agent's environmental understanding capability. Empirical evaluations show that our approach consistently outperforms baselines across various tasks and simulation environments. Extensive ablations studies attribute these gains to the Causal Understanding Module, which generalizes effectively in both Reinforcement and Supervised Learning settings without computational overhead.
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。