A Data-driven, Falsification-based Model of Human Driver Behavior
Abstract
We propose a novel framework to differentiate between vehicle trajectories originating from human and non-human drivers by constructing a data-driven boundary using parametric signal temporal logic (STL). Such construction allows us to evaluate the trajectories, detect rare-events, and reduce the uncertainty of driver behaviors when it assumes the form of a disturbance in control synthesis and evaluation problems. We train a classifier that separates admissible (i.e. human) examples - which arise from real-world demonstrations - and inadmissible (i.e. non-human) examples that are generated by falsifying specifications synthesized from the same real-world driving data. Proceeding in this fashion allows for finding a reasonable boundary of human behaviors exhibited in real-world driving records. The framework is demonstrated using a case study involving a human-driven vehicle approaching a signalized intersection.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2019
- DOI:
- 10.48550/arXiv.1912.08361
- arXiv:
- arXiv:1912.08361
- Bibcode:
- 2019arXiv191208361S
- Keywords:
-
- Computer Science - Robotics;
- Electrical Engineering and Systems Science - Systems and Control
- E-Print:
- ACC 2020. The first two authors contributed equally to this work