Robot Vitals and Robot Health: Towards Systematically Quantifying Runtime Performance Degradation in Robots Under Adverse Conditions

This letter addresses the problem of automatically detecting and quantifying performance degradation in remote mobile robots, real-time, during task execution. A robot may encounter a variety uncertainties adversities execution, which can impair its ability to carry out tasks effectively cause degrade. Such situations be mitigated or averted by timely detection intervention, e.g., human supervisor taking over control teleoperation mode. Inspired patient triaging systems hospitals, we introduce framework “robot vitals” for estimating overall health”. robot's vitals are set lower-level metrics that estimate indicators faced at any given point time. Robot health is higher-level metric combines into single scalar value degradation. Experiments, both simulation on real robot, demonstrate proposed used online estimation run-time.