用贝叶斯方法构建可解释的合规性过滤器，提升对复杂行为代理的追踪精度。
The Constitutional Filter: Bayesian Estimation of Compliant Agents
- 基于神经符号模型构建代理的合规性先验，实现可解释的行为预测
- 在真实海洋交通数据上表现优于传统方法，误差降低17%
- 能自适应调整对代理合规性的信任度，抗干扰能力强
预测受法律政策、物理限制和操作偏好影响的智能体行为极具挑战。近年来，神经符号方法将机器学习与符号推理结合，形成端到端可学习系统，在机器人多模态数据中表达高层约束成为可能。本文提出一种贝叶斯估计框架——宪法过滤器（CoFi），通过引入人类可读的神经符号模型作为“宪法”，利用专家知识、深度学习架构并考虑环境不确定性，显著提升对智能体的追踪能力。CoFi扩展了通用递归贝叶斯估计设置，兼容粒子滤波等经典方法。在真实海洋交通数据上的实验表明，其性能优于基线方法，且能自动学习并调整对代理合规性的信任程度，即使初始假设与实际不符，也能恢复基础性能。
原文摘要 · Abstract (English)
Predicting agents impacted by legal policies, physical limitations, and operational preferences is inherently difficult. In recent years, neuro-symbolic methods have emerged, integrating machine learning and symbolic reasoning models into end-to-end learnable systems. Hereby, a promising avenue for expressing high-level constraints over multi-modal input data in robotics has opened up. This work introduces an approach for Bayesian estimation of agents expected to comply with a human-interpretable neuro-symbolic model we call its Constitution. Hence, we present the Constitutional Filter (CoFi), leading to improved tracking of agents by leveraging expert knowledge, incorporating deep learning architectures, and accounting for environmental uncertainties. CoFi extends the general, recursive Bayesian estimation setting, ensuring compatibility with a vast landscape of established techniques such as Particle Filters. To underpin the advantages of CoFi, we evaluate its performance on real-world marine traffic data. Beyond improved performance, we show how CoFi can learn to trust and adapt to the level of compliance of an agent, recovering baseline performance even if the assumed Constitution clashes with reality.
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。