Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914859553128448 |
|---|---|
| author | Haritz, Pierre Wanke, David Liebig, Thomas |
| author_facet | Haritz, Pierre Wanke, David Liebig, Thomas |
| contents | Navigating unsignalized intersections in urban environments poses a complex challenge for self-driving vehicles, where issues such as view obstructions, unpredictable pedestrian crossings, and diverse traffic participants demand a great focus on crash prevention. In this paper, we propose a novel state representation for Reinforcement Learning (RL) agents centered around the information perceivable by an autonomous agent, enabling the safe navigation of previously uncharted road maps. Our approach surpasses several baseline models by a sig nificant margin in terms of safety and energy consumption metrics. These improvements are achieved while maintaining a competitive average travel speed. Our findings pave the way for more robust and reliable autonomous navigation strategies, promising safer and more efficient urban traffic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04343 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding Haritz, Pierre Wanke, David Liebig, Thomas Robotics Machine Learning Navigating unsignalized intersections in urban environments poses a complex challenge for self-driving vehicles, where issues such as view obstructions, unpredictable pedestrian crossings, and diverse traffic participants demand a great focus on crash prevention. In this paper, we propose a novel state representation for Reinforcement Learning (RL) agents centered around the information perceivable by an autonomous agent, enabling the safe navigation of previously uncharted road maps. Our approach surpasses several baseline models by a sig nificant margin in terms of safety and energy consumption metrics. These improvements are achieved while maintaining a competitive average travel speed. Our findings pave the way for more robust and reliable autonomous navigation strategies, promising safer and more efficient urban traffic environments. |
| title | Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2407.04343 |