Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.02546 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913415716405248 |
|---|---|
| author | Selvaraj, Dinesh Cyril Vitale, Christian Panayiotou, Tania Kolios, Panayiotis Chiasserini, Carla Fabiana Ellinas, Georgios |
| author_facet | Selvaraj, Dinesh Cyril Vitale, Christian Panayiotou, Tania Kolios, Panayiotis Chiasserini, Carla Fabiana Ellinas, Georgios |
| contents | In pursuit of autonomous vehicles, achieving human-like driving behavior is vital. This study introduces adaptive autopilot (AA), a unique framework utilizing constrained-deep reinforcement learning (C-DRL). AA aims to safely emulate human driving to reduce the necessity for driver intervention. Focusing on the car-following scenario, the process involves (i) extracting data from the highD natural driving study and categorizing it into three driving styles using a rule-based classifier; (ii) employing deep neural network (DNN) regressors to predict human-like acceleration across styles; and (iii) using C-DRL, specifically the soft actor-critic Lagrangian technique, to learn human-like safe driving policies. Results indicate effectiveness in each step, with the rule-based classifier distinguishing driving styles, the regressor model accurately predicting acceleration, outperforming traditional car-following models, and C-DRL agents learning optimal policies for humanlike driving across styles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02546 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Autopilot: Constrained DRL for Diverse Driving Behaviors Selvaraj, Dinesh Cyril Vitale, Christian Panayiotou, Tania Kolios, Panayiotis Chiasserini, Carla Fabiana Ellinas, Georgios Robotics Machine Learning In pursuit of autonomous vehicles, achieving human-like driving behavior is vital. This study introduces adaptive autopilot (AA), a unique framework utilizing constrained-deep reinforcement learning (C-DRL). AA aims to safely emulate human driving to reduce the necessity for driver intervention. Focusing on the car-following scenario, the process involves (i) extracting data from the highD natural driving study and categorizing it into three driving styles using a rule-based classifier; (ii) employing deep neural network (DNN) regressors to predict human-like acceleration across styles; and (iii) using C-DRL, specifically the soft actor-critic Lagrangian technique, to learn human-like safe driving policies. Results indicate effectiveness in each step, with the rule-based classifier distinguishing driving styles, the regressor model accurately predicting acceleration, outperforming traditional car-following models, and C-DRL agents learning optimal policies for humanlike driving across styles. |
| title | Adaptive Autopilot: Constrained DRL for Diverse Driving Behaviors |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2407.02546 |