.png){kind=icon}
返回
Learning vision based autonomous lateral vehicle control without supervision
.png){kind=icon}
OA
AI
DOI：10.1007/s10489-023-04478-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Supervised deep learning methods using image data as input have shown promising results in the context of vehicle control. However, these supervised methods have two main disadvantages: 1) They require a copious amount of labeled training data, which is difficult and expensive to collect. 2) Such models do not perform well, when situations that are not in the distribution of the training set are encountered. This includes deviations from the designated driving behavior. We therefore provide a framework to mitigate these problems from merely an unlabeled sequence of images. Visual Odometry is first used to determine the vehicle trajectory. Model Predictive Control (MPC) then uses this trajectory to implicitly infer the steering labels. Meanwhile, synthesized images at deviated trajectories are included in the training distribution for enhanced robustness of the neural network model. Experimental results demonstrate that the performance of our network is at par with methods requiring additional data collection or supervision. Code and supplementary information is available here:
Keyword:
Intelligent driving
Computer vision
Deep learning
Neural networks
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
A Magnetization Transfer Imaging Study of Normal-Appearing White Matter in Multiple Sclerosis.png)
Neurology
NeurologyIF0
PREAI
分享收藏Coordinated Trajectory-Tracking Control of a Marine Aerial-Surface Heterogeneous System海洋空面异构系统的协调轨迹跟踪控制
OAAI
OAAI分享收藏Risk factors associated with persistent chronic opioid use following THA与THA后持续慢性阿片类药物使用相关的危险因素
PREAI
分享收藏Pressure-Based Bioassay Perceived by a Flexible Pressure Sensor with Synergistic Enhancement of the Photothermal Effect通过具有协同增强光热效应的柔性压力传感器感知的基于压力的生物测定
PREAI
分享收藏
查看更多内容