DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning
Trajectory planning for automated vehicles in traffic has been a challenging task and a hot topic in recent research. The need for flexibility, transparency, interpretability and predictability poses challenges in deploying data-driven approaches in this safety-critical application. This paper propo...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10793110/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590350435221504 |
|---|---|
| author | Giovanni Lucente Mikkel Skov Maarssoe Sanath Himasekhar Konthala Anas Abulehia Reza Dariani Julian Schindler |
| author_facet | Giovanni Lucente Mikkel Skov Maarssoe Sanath Himasekhar Konthala Anas Abulehia Reza Dariani Julian Schindler |
| author_sort | Giovanni Lucente |
| collection | DOAJ |
| description | Trajectory planning for automated vehicles in traffic has been a challenging task and a hot topic in recent research. The need for flexibility, transparency, interpretability and predictability poses challenges in deploying data-driven approaches in this safety-critical application. This paper proposes DeepGame-TP, a game-theoretical trajectory planner that uses deep learning to model each agent’s cost function and adjust it based on observed behavior. In particular, a LSTM network predicts each agent’s desired speed, forming a penalizing term that reflects aggressiveness in the cost function. Experiments demonstrated significant advantages of this innovative framework, highlighting the adaptability of DeepGame-TP in intersection, overtaking, car following and merging scenarios. It effectively avoids dangerous situations that could arise from incorrect cost function estimates. The approach is suitable for real-time applications, solving the Generalized Nash Equilibrium Problem (GNEP) in scenarios with up to four vehicles in under 100 milliseconds on average. |
| format | Article |
| id | doaj-art-a711d2a5b3984581990331fe8417ca93 |
| institution | Kabale University |
| issn | 2687-7813 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj-art-a711d2a5b3984581990331fe8417ca932025-01-24T00:02:45ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132024-01-01587388810.1109/OJITS.2024.351527010793110DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory PlanningGiovanni Lucente0https://orcid.org/0000-0002-7844-853XMikkel Skov Maarssoe1https://orcid.org/0009-0003-9999-8711Sanath Himasekhar Konthala2https://orcid.org/0009-0008-4096-7685Anas Abulehia3https://orcid.org/0009-0009-3869-6748Reza Dariani4Julian Schindler5https://orcid.org/0000-0001-5398-8217Institute of Transportation Systems, German Aerospace Center (DLR), Braunschweig, GermanyInstitute of Transportation Systems, German Aerospace Center (DLR), Braunschweig, GermanyInstitute of Transportation Systems, German Aerospace Center (DLR), Braunschweig, GermanyInstitute of Transportation Systems, German Aerospace Center (DLR), Braunschweig, GermanyInstitute of Transportation Systems, German Aerospace Center (DLR), Braunschweig, GermanyInstitute of Transportation Systems, German Aerospace Center (DLR), Braunschweig, GermanyTrajectory planning for automated vehicles in traffic has been a challenging task and a hot topic in recent research. The need for flexibility, transparency, interpretability and predictability poses challenges in deploying data-driven approaches in this safety-critical application. This paper proposes DeepGame-TP, a game-theoretical trajectory planner that uses deep learning to model each agent’s cost function and adjust it based on observed behavior. In particular, a LSTM network predicts each agent’s desired speed, forming a penalizing term that reflects aggressiveness in the cost function. Experiments demonstrated significant advantages of this innovative framework, highlighting the adaptability of DeepGame-TP in intersection, overtaking, car following and merging scenarios. It effectively avoids dangerous situations that could arise from incorrect cost function estimates. The approach is suitable for real-time applications, solving the Generalized Nash Equilibrium Problem (GNEP) in scenarios with up to four vehicles in under 100 milliseconds on average.https://ieeexplore.ieee.org/document/10793110/Dynamic gamedeep learninggeneralized Nash equilibriumLSTMtrajectory planning |
| spellingShingle | Giovanni Lucente Mikkel Skov Maarssoe Sanath Himasekhar Konthala Anas Abulehia Reza Dariani Julian Schindler DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning IEEE Open Journal of Intelligent Transportation Systems Dynamic game deep learning generalized Nash equilibrium LSTM trajectory planning |
| title | DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning |
| title_full | DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning |
| title_fullStr | DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning |
| title_full_unstemmed | DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning |
| title_short | DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning |
| title_sort | deepgame tp integrating dynamic game theory and deep learning for trajectory planning |
| topic | Dynamic game deep learning generalized Nash equilibrium LSTM trajectory planning |
| url | https://ieeexplore.ieee.org/document/10793110/ |
| work_keys_str_mv | AT giovannilucente deepgametpintegratingdynamicgametheoryanddeeplearningfortrajectoryplanning AT mikkelskovmaarssoe deepgametpintegratingdynamicgametheoryanddeeplearningfortrajectoryplanning AT sanathhimasekharkonthala deepgametpintegratingdynamicgametheoryanddeeplearningfortrajectoryplanning AT anasabulehia deepgametpintegratingdynamicgametheoryanddeeplearningfortrajectoryplanning AT rezadariani deepgametpintegratingdynamicgametheoryanddeeplearningfortrajectoryplanning AT julianschindler deepgametpintegratingdynamicgametheoryanddeeplearningfortrajectoryplanning |