Behavioral Cloning for Driverless Cars using Transfer Learning

Xin Zhang, Maolin Chen, Xingqun Zhan

Abstract: A machine learning algorithm for decision making in driverless navigation is developed. This method is implemented through adapting existing proved convolutional neural networks to the current problem. Compared to the traditional methods supported by algorithms from computer graphics, this transfer learning method tend to optimize all processing steps simultaneously, thus leading to better performance while maintaining a high performance-to-cost ratio.
Published in: 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS)
April 23 - 26, 2018
Hyatt Regency Hotel
Monterey, CA
Pages: 1069 - 1073
Cite this article: Zhang, Xin, Chen, Maolin, Zhan, Xingqun, "Behavioral Cloning for Driverless Cars using Transfer Learning," 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, April 2018, pp. 1069-1073.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In