Teaching Autonomous Vehicles How to Drive under Sensing Exceptions by Human Driving Demonstrations

2017-01-0070

03/28/2017

Event
WCX™ 17: SAE World Congress Experience
Authors Abstract
Content
Autonomous driving technologies can provide better safety, comfort and efficiency for future transportation systems. Most research in this area has mainly been focused on developing sensing and control approaches to achieve various autonomous driving functions. Very little of this research, however, has studied how to efficiently handle sensing exceptions. A simple exception measured by any of the sensors may lead to failures in autonomous driving functions. The autonomous vehicles are then supposed to be sent back to manufacturers for repair, which takes both time and money. This paper introduces an efficient approach to make human drivers able to online teach autonomous vehicles to drive under sensing exceptions. A human-vehicle teaching-and-learning framework for autonomous driving is proposed and the human teaching and vehicle learning processes for handling sensing exceptions in autonomous vehicles are designed in detail. Experimental results acquired from a 1/10-scale autonomous driving vehicle illustrate the effectiveness and advantages of the proposed approach.
Meta TagsDetails
DOI
https://doi.org/10.4271/2017-01-0070
Pages
8
Citation
Guo, L., Manglani, S., Li, X., and Jia, Y., "Teaching Autonomous Vehicles How to Drive under Sensing Exceptions by Human Driving Demonstrations," SAE Technical Paper 2017-01-0070, 2017, https://doi.org/10.4271/2017-01-0070.
Additional Details
Publisher
Published
Mar 28, 2017
Product Code
2017-01-0070
Content Type
Technical Paper
Language
English