提出可实现实体机器人部署的社交导航强化学习框架，解决仿真到现实的动态差异问题。
KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility
- 用高阶控制输入替代传统一阶动作空间，提升仿真与真实机器人的轨迹一致性。
- 基于2D LiDAR的聚类追踪算法，实现稳定行人速度估计且无需多传感器融合。
- 引入无偏残差门控模块，平衡反应与记忆行为，适应不同人数的复杂人群场景。
深度强化学习在社交导航中展现潜力，但其在真实世界的部署仍受制于仿真到现实的差距，主要源于简化的前向动力学模型和依赖特定上下文的人类状态估计流程。本文提出统一框架KinematicRL，以生成适用于真实部署的动态可行导航策略。首先，理论分析表明，模拟与实际机器人位置的跟踪误差随控制阶数升高呈指数衰减，据此采用更高阶控制输入作为DRL动作空间；针对差速驱动机器人设计了二阶控制形式，并结合随机迭代线性二次调节器（iLQR）通过最小化发散目标预训练策略。其次，为避免相机-激光雷达融合带来的系统复杂性，提出仅使用2D LiDAR的聚类式人类追踪管道：基于空间邻近性和速度相似性进行检测关联，通过时间聚合实现对近距离行人的可靠区分与稳定速度估计。第三，引入无偏残差门控块，平衡反应式与记忆式行为，有效应对时变人群规模。实验表明，结合所提追踪方案，KinematicRL可在真实差速驱动机器人上以极小改动完成部署，显著提升运动学表现并自适应不同数量的人类检测。
原文摘要 · Abstract (English)
Deep Reinforcement Learning (DRL) has shown promise for social navigation, yet its real-world deployment remains hindered by a persistent sim-to-real gap arising from simplified first-order dynamics and context-specific human state estimation pipelines. This work presents a unified framework that addresses these limitations to produce dynamically feasible navigation policies suitable for real-world deployment. First, theoretical analysis reveals that tracking error between simulated and actual robot position decays exponentially with increased control order, motivating the use of higher-order control inputs as DRL action space. A second-order control formulation tailored to differential drive robots is developed, complemented by a stochastic iterative Linear Quadratic Regulator (iLQR) that pretrains the policy via a divergence minimization objective. Second, to avoid the added system complexity of camera-LiDAR fusion, a cluster-based human tracking pipeline using only 2D LiDAR is introduced. Human detections are associated according to both spatial proximity and velocity similarity, enabling reliable differentiation of nearby pedestrians and yielding stable velocity estimates through temporal aggregation. Third, we introduce an unbiased residual gating block to balance reaction- and memory-based behaviors while handling time-varying crowd sizes, both critical for social navigation. The resulting policy, KinematicRL, consistently improves kinematic performance and adapts to varying number of detected humans. Experiments in real-world environments demonstrate that, when combined with the proposed tracking pipeline, KinematicRL can be deployed on a real differential drive robot with minimal modifications.
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。