State Prediction of Human-in-the-Loop Multi-rotor System with Stochastic Human Behavior Model

• DOI: 10.48550/arxiv.2207.03318
• Publication Date: 2022-01-01
• Authors: Joonwon Choi; Sooyung Byeon; Inseok Hwang
• Keywords: 0209 industrial biotechnology; FOS: Electrical engineering, electronic engineering, information engineering; Systems and Control (eess.SY); 02 engineering and technology; Electrical Engineering and Systems Science - Systems and Control

Reachability analysis is a widely used method to analyze the safety of Human-in-the-Loop Cyber Physical System (HiLCPS). This strategy allows HiLCPS respond against an imminent threat in advance by predicting reachable states system. However, it could lead unnecessarily conservative set if prediction only relies on system dynamics without explicitly considering human behavior, and thus risk might be overestimated. To reduce conservativeness reachability analysis, we present state which takes into account stochastic behavior model represented as Gaussian Mixture Model (GMM). In this paper, focus multi-rotor near-collision situation. The trained using experimental data represent operators' evasive maneuver. Then, can retrieve control input probability distribution from Regression (GMR). proposed algorithm predicts multi-rotor's future based given retrieved distribution. Besides, considers uncertainty initial modeled GMM, yields more robust performance. Human subject experiment results are provided demonstrate effectiveness algorithm.