Interpretable Run-Time Prediction and Planning in Co-Robotic Environments
Interpretable Run-Time Prediction and Planning in Co-Robotic Environments
复制标题
DOI：
10.1109/iros51168.2021.9636282
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Rahul Peddi;N. Bezzo
中科院分区：
文献类型：
--
作者：
Rahul Peddi;N. Bezzo
传统上，移动的机器人被开发为反应性的，并避免与周围的人类发生碰撞，通常以不自然的方式移动而不遵循社交协议，迫使人们的行为与人与人之间的交互规则非常不同。另一方面，人类能够无缝地理解为什么他们可能会干扰周围的人，并根据他们的推理改变他们的行为，从而产生平滑，直观的回避行为。在本文中，我们提出了一种方法，移动的机器人，以避免干扰周围的人类所需的路径。我们利用先前观察到的轨迹库来设计基于决策树的可解释监视器，该监视器：i）预测机器人是否干扰周围的人类，ii）解释导致预测的行为，iii）如果预测到干扰，则计划纠正行为。我们还提出了一个验证计划，以改善预测模型在运行时。所提出的方法进行了验证与仿真和实验，涉及一个无人驾驶地面车辆（UGV）在人类的存在下执行去目标操作，展示非干扰行为和运行时学习。
Mobile robots are traditionally developed to be reactive and avoid collisions with surrounding humans, often moving in unnatural ways without following social protocols, forcing people to behave very differently from human-human interaction rules. Humans, on the other hand, are seamlessly able to understand why they may interfere with surrounding humans and change their behavior based on their reasoning, resulting in smooth, intuitive avoiding behaviors. In this paper, we propose an approach for a mobile robot to avoid interfering with the desired paths of surrounding humans. We leverage a library of previously observed trajectories to design a decision-tree based interpretable monitor that: i) predicts whether the robot is interfering with surrounding humans, ii) explains what behaviors are causing either prediction, and iii) plans corrective behaviors if interference is predicted. We also propose a validation scheme to improve the predictive model at run-time. The proposed approach is validated with simulations and experiments involving an unmanned ground vehicle (UGV) performing go-to-goal operations in the presence of humans, demonstrating non-interfering behaviors and run-time learning.