Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma
We address the problem of predicting whether a driver facing the yellow-light-dilemma will cross the intersection with the red light. Based on driving simulator data, we propose a stochastic hybrid system model for driver behavior. Using this model combined with Gaussian process estimation and Monte...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/109181 https://orcid.org/0000-0003-1866-6970 https://orcid.org/0000-0001-6472-8576 |
| _version_ | 1811091576200364032 |
|---|---|
| author | Green, Paul A. Hoehener, Daniel Andreas Del Vecchio, Domitilla |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Green, Paul A. Hoehener, Daniel Andreas Del Vecchio, Domitilla |
| author_sort | Green, Paul A. |
| collection | MIT |
| description | We address the problem of predicting whether a driver facing the yellow-light-dilemma will cross the intersection with the red light. Based on driving simulator data, we propose a stochastic hybrid system model for driver behavior. Using this model combined with Gaussian process estimation and Monte Carlo simulations, we obtain an upper bound for the probability of crossing with the red light. This upper bound has a prescribed confidence level and can be calculated quickly on-line in a recursive fashion as more data become available. Calculating also a lower bound we can show that the upper bound is on average less than 3% higher than the true probability. Moreover, tests on driving simulator data show that 99% of the actual red light violations, are predicted to cross on red with probability greater than 0.95 while less than 5% of the compliant trajectories are predicted to have an equally high probability of crossing. Determining the probability of crossing with the red light will be important for the development of warning systems that prevent red light violations. |
| first_indexed | 2024-09-23T15:04:34Z |
| format | Article |
| id | mit-1721.1/109181 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:04:34Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1091812022-09-29T12:32:01Z Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma Green, Paul A. Hoehener, Daniel Andreas Del Vecchio, Domitilla Massachusetts Institute of Technology. Department of Mechanical Engineering Hoehener, Daniel Andreas Del Vecchio, Domitilla We address the problem of predicting whether a driver facing the yellow-light-dilemma will cross the intersection with the red light. Based on driving simulator data, we propose a stochastic hybrid system model for driver behavior. Using this model combined with Gaussian process estimation and Monte Carlo simulations, we obtain an upper bound for the probability of crossing with the red light. This upper bound has a prescribed confidence level and can be calculated quickly on-line in a recursive fashion as more data become available. Calculating also a lower bound we can show that the upper bound is on average less than 3% higher than the true probability. Moreover, tests on driving simulator data show that 99% of the actual red light violations, are predicted to cross on red with probability greater than 0.95 while less than 5% of the compliant trajectories are predicted to have an equally high probability of crossing. Determining the probability of crossing with the red light will be important for the development of warning systems that prevent red light violations. 2017-05-18T20:07:11Z 2017-05-18T20:07:11Z 2015-07 2015-07 Article http://purl.org/eprint/type/ConferencePaper 978-1-4799-8684-2 0743-1619 2378-5861 http://hdl.handle.net/1721.1/109181 Hoehener, Daniel; Green, Paul A. and Del Vecchio, Domitilla. “Stochastic Hybrid Models for Predicting the Behavior of Drivers Facing the Yellow-Light-Dilemma.” 2015 American Control Conference (ACC), July 1-3 2015, Chicago, Illinois, Institute of Electrical and Electronics Engineers (IEEE), July 2015 https://orcid.org/0000-0003-1866-6970 https://orcid.org/0000-0001-6472-8576 en_US http://dx.doi.org/10.1109/ACC.2015.7171849 American Control Conference (ACC), 2015 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT Web Domain |
| spellingShingle | Green, Paul A. Hoehener, Daniel Andreas Del Vecchio, Domitilla Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma |
| title | Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma |
| title_full | Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma |
| title_fullStr | Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma |
| title_full_unstemmed | Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma |
| title_short | Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma |
| title_sort | stochastic hybrid models for predicting the behavior of drivers facing the yellow light dilemma |
| url | http://hdl.handle.net/1721.1/109181 https://orcid.org/0000-0003-1866-6970 https://orcid.org/0000-0001-6472-8576 |
| work_keys_str_mv | AT greenpaula stochastichybridmodelsforpredictingthebehaviorofdriversfacingtheyellowlightdilemma AT hoehenerdanielandreas stochastichybridmodelsforpredictingthebehaviorofdriversfacingtheyellowlightdilemma AT delvecchiodomitilla stochastichybridmodelsforpredictingthebehaviorofdriversfacingtheyellowlightdilemma |