Learning driving behavior by timed syntactic pattern recognition

Authors:
Sicco Verwer;Mathijs De Weerdt;Cees Witteveen
Affiliations:
Katholieke Universiteit Leuven, Leuven, Belgium;Delft University of Technology, Delft, The Netherlands;Delft University of Technology, Delft, The Netherlands
Venue:
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Year:
2011

Citing 9
Cited 1

A theory of timed automata

Theoretical Computer Science
Real-time automata

Journal of Automata, Languages and Combinatorics
Introduction to the Theory of Computation

Introduction to the Theory of Computation
A Survey of Temporal Knowledge Discovery Paradigms and Methods

IEEE Transactions on Knowledge and Data Engineering
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
One-Clock Deterministic Timed Automata Are Efficiently Identifiable in the Limit

LATA '09 Proceedings of the 3rd International Conference on Language and Automata Theory and Applications
Introduction to Semi-Supervised Learning

Introduction to Semi-Supervised Learning
A bibliographical study of grammatical inference

Pattern Recognition
A likelihood-ratio test for identifying probabilistic deterministic real-time automata from positive data

ICGI'10 Proceedings of the 10th international colloquium conference on Grammatical inference: theoretical results and applications

Map matching with inverse reinforcement learning

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We advocate the use of an explicit time representation in syntactic pattern recognition because it can result in more succinct models and easier learning problems. We apply this approach to the real-world problem of learning models for the driving behavior of truck drivers. We discretize the values of onboard sensors into simple events. Instead of the common syntactic pattern recognition approach of sampling the signal values at a fixed rate, we model the time constraints using timed models. We learn these models using the RTI+ algorithm from grammatical inference, and show how to use computational mechanics and a form of semi-supervised classification to construct a real-time automaton classifier for driving behavior. Promising results are shown using this new approach.