SANGO让机器人在人群里安全绕行，自动分组障碍物并遵守社交距离。
SANGO: Socially Aware Navigation through Grouped Obstacles
- 用DBSCAN聚类障碍物，结合PPO强化学习规划路径。
- 使不适感降低83.5%，碰撞率减少29.4%，导航成功率更高。
- 适合智能机器人、自动驾驶等需社交互动的场景。
本文提出SANGO（Socially Aware Navigation through Grouped Obstacles），一种通过动态分组障碍物并遵循社交规范来实现社会适宜行为的新方法。该方法利用深度强化学习，结合DBSCAN算法进行障碍物聚类，采用近端策略优化（PPO）进行路径规划。实验在自建仿真环境中开展，结果表明，SANGO显著提升了安全性与社会合规性，使不适感降低最多达83.5%，碰撞率减少最多达29.4%，在动态拥挤场景中实现了更高的成功导航率。这些发现凸显了SANGO在真实世界应用中的潜力，为先进社交感知机器人导航系统的发展铺平了道路。
原文摘要 · Abstract (English)
This paper introduces SANGO (Socially Aware Navigation through Grouped Obstacles), a novel method that ensures socially appropriate behavior by dynamically grouping obstacles and adhering to social norms. Using deep reinforcement learning, SANGO trains agents to navigate complex environments leveraging the DBSCAN algorithm for obstacle clustering and Proximal Policy Optimization (PPO) for path planning. The proposed approach improves safety and social compliance by maintaining appropriate distances and reducing collision rates. Extensive experiments conducted in custom simulation environments demonstrate SANGO's superior performance in significantly reducing discomfort (by up to 83.5%), reducing collision rates (by up to 29.4%) and achieving higher successful navigation in dynamic and crowded scenarios. These findings highlight the potential of SANGO for real-world applications, paving the way for advanced socially adept robotic navigation systems.
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。