This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Handling Deviation for Autonomous Vehicles after Learning from Small Dataset
Technical Paper
2018-01-1091
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Learning only from a small set of examples remains a huge challenge in machine learning. Despite recent breakthroughs in the applications of neural networks, the applicability of these techniques has been limited by the requirement for large amounts of training data. What’s more, the standard supervised machine learning method does not provide a satisfactory solution for learning new concepts from little data. However, the ability to learn enough information from few samples has been demonstrated in humans. This suggests that humans may make use of prior knowledge of a previously learned model when learning new ones on a small amount of training examples. In the area of autonomous driving, the model learns to drive the vehicle with training data from humans, and most machine learning based control algorithms require training on very large datasets. Collecting and constructing training data set takes a huge amount of time and needs specific knowledge to gather relevant information. This paper aims to learn control parameters from only a few training images. We build a simple control system which can use prior knowledge to correct parameters when the vehicle deviates from the training route, and allows for learning on a few training examples. The system introduces a new architecture that when combined with neural networks, significantly lowers the amount of data required to make meaningful predictions and improves the ability to learn meaningful information on the surrounding environment in never before seen scenarios. We test a simple implementation of our algorithm on a 1/10-scale autonomous driving vehicle. The proposed models produce effective control commands in some untrained lane deviation scenarios, when the number of training examples is normally too small for traditional machine learning methods to work, and allows the vehicle to find the correct track in the lane.
Recommended Content
Authors
Topic
Citation
Zhang, Z., Zhang, Z., Guo, L., Wang, W. et al., "Handling Deviation for Autonomous Vehicles after Learning from Small Dataset," SAE Technical Paper 2018-01-1091, 2018, https://doi.org/10.4271/2018-01-1091.Also In
References
- Behmann , F. and Wu , K. Collaborative Internet of Things (C-IoT): For Future Smart Connected Life and Business John Wiley & Sons 2015
- Kuderer , M. , Gulati , S. , and Burgard , W. Learning Driving Styles for Autonomous Vehicles from Demonstration 2015 IEEE International Conference on Robotics and Automation (ICRA) 2015
- Zhou , M. , Qu , X. , and Jin , S. On the Impact of Cooperative Autonomous Vehicles in Improving Freeway Merging: A Modified Intelligent Driver Model-Based Approach IEEE Transactions on Intelligent Transportation Systems 18 6 1422 1428 2017
- Urmson , C. et al. Autonomous Driving in Urban Environments: Boss and the Urban Challenge The DARPA Urban Challenge Springer 2009 1 59
- Sallab , A.E. , Abdou , M. , Perot , E. , and Yogamani , S. Deep Reinforcement Learning Framework for Autonomous Driving Electronic Imaging 2017 19 70 76 2017
- Xu , H. et al. End-to-End Learning of Driving Models from Large-Scale Video Datasets arXiv preprint arXiv 1612 01079 2016
- Bojarski , M. et al. End to End Learning for Self-Driving Cars arXiv preprint arXiv 1604 07316 2016
- Bojarski , M. et al. Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car arXiv preprint arXiv 1704 07911 2017
- Johnson-Roberson , M. et al. Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks? 2017 IEEE International Conference on Robotics and Automation (ICRA) 2017
- Sun , C. et al. Revisiting Unreasonable Effectiveness of Data in Deep Learning Era arXiv preprint arXiv 1707 02968 2017
- Guo , L. et al. Teaching Autonomous Vehicles How to Drive under Sensing Exceptions by Human Driving Demonstrations SAE Technical Paper 2017-01-0070 2017 10.4271/2017-01-0070
- Dagli , C.H. Artificial Neural Networks for Intelligent Manufacturing Springer Science & Business Media 2012
- Sotiras , A. , Davatzikos , C. , and Paragios , N. Deformable Medical Image Registration: A Survey IEEE Transactions on Medical Imaging 32 7 1153 1190 2013
- Tsin , Y. and Kanade , T. A Correlation-Based Approach to Robust Point Set Registration European Conference on Computer Vision
- Ma , J. , et al. Robust Estimation of Nonrigid Transformation for Point Set Registration Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2013