Reinforcement Learning for Online Testing of Autonomous Driving Systems: a Replication and Extension Study
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911805739106304 |
|---|---|
| author | Giamattei, Luca Biagiola, Matteo Pietrantuono, Roberto Russo, Stefano Tonella, Paolo |
| author_facet | Giamattei, Luca Biagiola, Matteo Pietrantuono, Roberto Russo, Stefano Tonella, Paolo |
| contents | In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective search) for online testing of Deep Neural Network-enabled systems. The empirical evaluation of these techniques was conducted on a state-of-the-art Autonomous Driving System (ADS). This work is a replication and extension of that empirical study. Our replication shows that RL does not outperform pure random test generation in a comparison conducted under the same settings of the original study, but with no confounding factor coming from the way collisions are measured. Our extension aims at eliminating some of the possible reasons for the poor performance of RL observed in our replication: (1) the presence of reward components providing contrasting or useless feedback to the RL agent; (2) the usage of an RL algorithm (Q-learning) which requires discretization of an intrinsically continuous state space. Results show that our new RL agent is able to converge to an effective policy that outperforms random testing. Results also highlight other possible improvements, which open to further investigations on how to best leverage RL for online ADS testing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13729 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reinforcement Learning for Online Testing of Autonomous Driving Systems: a Replication and Extension Study Giamattei, Luca Biagiola, Matteo Pietrantuono, Roberto Russo, Stefano Tonella, Paolo Software Engineering Artificial Intelligence Machine Learning Robotics In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective search) for online testing of Deep Neural Network-enabled systems. The empirical evaluation of these techniques was conducted on a state-of-the-art Autonomous Driving System (ADS). This work is a replication and extension of that empirical study. Our replication shows that RL does not outperform pure random test generation in a comparison conducted under the same settings of the original study, but with no confounding factor coming from the way collisions are measured. Our extension aims at eliminating some of the possible reasons for the poor performance of RL observed in our replication: (1) the presence of reward components providing contrasting or useless feedback to the RL agent; (2) the usage of an RL algorithm (Q-learning) which requires discretization of an intrinsically continuous state space. Results show that our new RL agent is able to converge to an effective policy that outperforms random testing. Results also highlight other possible improvements, which open to further investigations on how to best leverage RL for online ADS testing. |
| title | Reinforcement Learning for Online Testing of Autonomous Driving Systems: a Replication and Extension Study |
| topic | Software Engineering Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2403.13729 |