Purdue University Graduate School
Browse
- No file added yet -

REACHABILITY ANALYSIS OF HUMAN-IN-THE-LOOP SYSTEMS USING GAUSSIAN MIXTURE MODEL WITH SIDE INFORMATION

Download (4.46 MB)
Version 2 2024-05-15, 15:20
Version 1 2024-05-08, 17:31
thesis
posted on 2024-05-15, 15:20 authored by Cheng-Han YangCheng-Han Yang

In the context of a Human-in-the-Loop (HITL) system, the accuracy of reachability analysis plays a significant role in ensuring the safety and reliability of HITL systems. In addition, one can avoid unnecessary conservativeness by explicitly considering human control behavior compared to those methods that rely on the system dynamics alone. One possible approach is to use a Gaussian Mixture Model (GMM) to encode human control behavior using the Expectation-Maximization (EM) algorithm. However, relatively few works consider the admissible control input ranges due to physical limitations when modeling human control behavior. This could make the following reachability analysis overestimate the system's capability, thereby affecting the performance of the HITL system. To address this issue, this work presents a constrained stochastic reachability analysis algorithm that can explicitly account for the admissible control input ranges. By confining the ellipsoidal confidence region of each Gaussian component using Sequential Quadratic Programming (SQP), we probabilistically constrain the GMM as well as the corresponding stochastic reachable sets. A comprehensive mathematical analysis of how the constrained GMM can affect the stochastic reachable sets is provided in this work. Finally, the proposed stochastic reachability analysis algorithm is validated via an illustrative numerical example.

Funding

CPS: Frontier: Collaborative Research: Cognitive Autonomy for Human CPS: Turning Novices into Experts

Directorate for Computer & Information Science & Engineering

Find out more...

History

Degree Type

  • Master of Science in Aeronautics and Astronautics

Department

  • Aeronautics and Astronautics

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Inseok Hwang

Additional Committee Member 2

Dengfeng Sun

Additional Committee Member 3

Ran Dai