Autonomous mobile robots (AMR) operating in the real world often need to make critical decisions that directly impact their own safety and the safety of their surroundings. Learning-based approaches for decision making have gained popularity in recent years, since decisions can be made very quickly and with reasonable levels of accuracy for many applications. These approaches, however, typically return only one decision, and if the learner is poorly trained or observations are noisy, the decision may be incorrect. This problem is further exacerbated when the robot is making decisions about its own failures, such as faulty actuators or sensors and external disturbances, when a wrong decision can immediately cause damage to the robot. In this paper, we consider this very case study: a robot dealing with such failures must quickly assess uncertainties and make safe decisions. We propose an uncertainty aware learning-based failure detection and recovery approach, in which we leverage Decision Tree theory along with Model Predictive Control to detect and explain which failure is compromising the system, assess uncertainties associated with the failure, and lastly, find and validate corrective controls to recover the system. Our approach is validated with simulations and real experiments on a faulty unmanned ground vehicle (UGV) navigation case study, demonstrating recovery to safety under uncertainties.

翻译：在现实世界中运行的自主移动机器人（AMR）通常需要做出直接关乎自身及周围环境安全的关键决策。基于学习的决策方法近年来广受欢迎，因为这类方法能以较快速度和合理精度处理众多应用场景。然而，这些方法通常仅返回单一决策结果，若模型训练不充分或观测数据存在噪声，该决策可能出现偏差。当机器人需要针对自身故障（如执行器/传感器异常或外部扰动）进行决策时，此类问题尤为严峻——错误决策可能直接对机器人造成物理损伤。本文聚焦这一典型案例：面临此类故障的机器人必须快速评估不确定性并做出安全决策。我们提出一种不确定性感知的基于学习的故障检测与恢复方法，该方法结合决策树理论与模型预测控制，实现以下目标：检测并解释导致系统异常的故障类型；评估与故障相关的不确定性；最终寻找并验证可恢复系统的校正控制策略。通过故障无人地面车辆（UGV）导航案例的仿真与真实实验验证，证明该方法能在不确定性条件下实现安全恢复。