陌生人危险！在基于强化学习的社交机器人导航中识别并避开不可预测的行人
Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation
AI总结：
针对基于强化学习的社交机器人导航在陌生场景下性能下降的问题，通过改进SARL策略的训练流程、价值网络和奖励函数，在保持导航效率的同时大幅提升了应对不可预测行人的安全性，且方法可迁移。
摘要：
用于社交机器人导航的强化学习（RL）方法在机器人穿越大量人群的导航任务中取得了显著成功，但由于这类方法依赖具有代表性的训练数据，在极具挑战性或陌生的场景下性能往往会下降。为保障人类的安全与舒适，这些算法必须能妥善处理罕见情况，但此类情况发生频率低、种类多样，给这些数据驱动方法带来了巨大挑战。为克服这一难题，我们对学习过程提出改进，促使这些RL策略在陌生场景下保持更高的警惕性。具体而言，我们对社交注意力强化学习（Socially Attentive Reinforcement Learning, SARL）策略进行了三方面优化：（1）修改训练流程，系统性地向行人模型中引入偏差；（2）更新价值网络，以估计并利用行人不可预测性特征；（3）设计奖励函数，学习对行人不可预测性的有效应对方式。与原始SARL策略相比，我们改进后的策略保持了相近的导航时间和路径长度，同时在最困难的场景下碰撞次数减少了82%，处于行人个人空间内的时间占比最高降低了19个百分点。我们还说明了如何将这些改进应用到其他RL策略中，并证明了我们方法的一些关键高层行为可迁移到实体机器人上。
英文摘要：
Reinforcement learning (RL) methods for social robot navigation show great success navigating robots through large crowds of people, but the performance of these learning-based methods tends to degrade in particularly challenging or unfamiliar situations due to the models' dependency on representative training data. To ensure human safety and comfort, it is critical that these algorithms handle uncommon cases appropriately, but the low frequency and wide diversity of such situations present a significant challenge for these data-driven methods. To overcome this challenge, we propose modifications to the learning process that encourage these RL policies to maintain additional caution in unfamiliar situations. Specifically, we improve the Socially Attentive Reinforcement Learning (SARL) policy by (1) modifying the training process to systematically introduce deviations into a pedestrian model, (2) updating the value network to estimate and utilize pedestrian-unpredictability features, and (3) implementing a reward function to learn an effective response to pedestrian unpredictability. Compared to the original SARL policy, our modified policy maintains similar navigation times and path lengths, while reducing the number of collisions by 82% and reducing the proportion of time spent in the pedestrians' personal space by up to 19 percentage points for the most difficult cases. We also describe how to apply these modifications to other RL policies and demonstrate that some key high-level behaviors of our approach transfer to a physical robot.
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。
