迈向可解释的人机交互:一种主动推断方法用于遮挡行人场景
Towards Intelligible Human-Robot Interaction: An Active Inference Approach to Occluded Pedestrian Scenarios
AI总结:
本文提出基于主动推断的方法,用于解决遮挡行人场景中的安全挑战,通过结合 RBPF 和 CEM 增强的 MPPI 控制器,实现可解释的人机交互。
摘要:
遮挡行人突然出现是自动驾驶中的关键安全挑战。传统基于规则或纯数据驱动的方法难以应对这些长尾场景固有的高不确定性。为解决这一挑战,我们提出了一种基于主动推断的新框架,使智能体具备人类似似的信念驱动机制。我们的框架利用 Rao-Blackwellized Particle Filter (RBPF) 高效估计行人混合状态。为模拟在不确定性下的人类似认知过程,我们引入了条件信念重置机制和假设注入技术,以显式建模行人多个潜在意图的信念。通过增强的 Model Predictive Path Integral (MPPI) 控制器实现规划,该控制器结合了 CEM 的高效迭代搜索与 MPPI 内在的鲁棒性。模拟实验表明,我们的方法相比反应式、基于规则和强化学习 (RL) 基线显著降低了碰撞率,同时表现出可解释且人类似的驾驶行为,反映了智能体内部的信念状态。
英文摘要:
The sudden appearance of occluded pedestrians presents a critical safety challenge in autonomous driving. Conventional rule-based or purely data-driven approaches struggle with the inherent high uncertainty of these long-tail scenarios. To tackle this challenge, we propose a novel framework grounded in Active Inference, which endows the agent with a human-like, belief-driven mechanism. Our framework leverages a Rao-Blackwellized Particle Filter (RBPF) to efficiently estimate the pedestrian's hybrid state. To emulate human-like cognitive processes under uncertainty, we introduce a Conditional Belief Reset mechanism and a Hypothesis Injection technique to explicitly model beliefs about the pedestrian's multiple latent intentions. Planning is achieved via a Cross-Entropy Method (CEM) enhanced Model Predictive Path Integral (MPPI) controller, which synergizes the efficient, iterative search of CEM with the inherent robustness of MPPI. Simulation experiments demonstrate that our approach significantly reduces the collision rate compared to reactive, rule-based, and reinforcement learning (RL) baselines, while also exhibiting explainable and human-like driving behavior that reflects the agent's internal belief state.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。