Deep reinforcement learning navigation via decision transformer in autonomous driving
Problem
Improving navigation decision-making for autonomous vehicles in partially observable urban environments with sensor noise and occlusion.
Why it matters
Reliable autonomous driving decisions in complex urban settings are critical for safety and deployment of self-driving technology.
What the AI did
The DRLNDT framework combines Soft Actor-Critic reinforcement learning with Transformer neural networks to model temporal dependencies in observations and actions for navigation decisions.
Results
not stated in source
Impact
The evidence supports that the algorithm was proposed to address the challenge but no concrete benchmark results are visible in the abstract.
Record
| Venue | Frontiers in Neurorobotics |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Lun Ge, Xiaoguang Zhou, Yongqiang Li, Yongcong Wang |
| Citations | 23 (OpenAlex, at import time) |
| References | 54 |
| Model or method | DRLNDT (SAC + Decision Transformer) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3389/fnbot.2024.1338189 |
| Open access | gold |
| Keywords | deep reinforcement learning, decision transformer, autonomous driving, navigation, SAC |
Importance rating
significant — thousands to millions affected
Autonomous driving navigation in partially observable urban environments is safety-critical for self-driving deployment; abstract gives no scale or results.
More in Robotics & Autonomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Autonomous robotic laparoscopic surgery for intestinal anastomosis | 2022 | 384 |
7
|
| 2 | Solving Rubik's Cube with a Robot Hand | 2019 | 569 |
6
|
| 3 | PaLM-E: An Embodied Multimodal Language Model | 2023 | 346 |
6
|
| 4 | Assistive Navigation Using Deep Reinforcement Learning Guiding Robot With UWB/Voice Beacons and Semantic Feedbacks for Blind and Visually Impaired People | 2021 | 48 |
6
|
| 5 | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges | 2022 | 154 |
6
|