Sample Efficient Interactive End-to-End Deep Learning for Self-Driving Cars with Selective Multi-Class Safe Dataset Aggregation

Yunus Bicer, Ali Alizadeh, Nazim Kemal Ure, Ahmetcan Erdogan, Orkun Kizilirmak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Citations (Scopus)

Abstract

The objective of this paper is to develop a sample efficient end-to-end deep learning method for self-driving cars, where we attempt to increase the value of the information extracted from samples, through careful analysis obtained from each call to expert driver's policy. End-to-end imitation learning is a popular method for computing self-driving car policies. The standard approach relies on collecting pairs of inputs (camera images) and outputs (steering angle, etc.) from an expert policy and fitting a deep neural network to this data to learn the driving policy. Although this approach had some successful demonstrations in the past, learning a good policy might require a lot of samples from the expert driver, which might be resource-consuming. In this work, we develop a novel framework based on the Safe Dataset Aggregation (safe DAgger) approach, where the current learned policy is automatically segmented into different trajectory classes, and the algorithm identifies trajectory segments/classes with the weak performance at each step. Once the trajectory segments with weak performance identified, the sampling algorithm focuses on calling the expert policy only on these segments, which improves the convergence rate. The presented simulation results show that the proposed approach can yield significantly better performance compared to the standard Safe DAgger algorithm while using the same amount of samples from the expert.

Original languageEnglish
Title of host publication2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2629-2634
Number of pages6
ISBN (Electronic)9781728140049
DOIs
Publication statusPublished - Nov 2019
Event2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019 - Macau, China
Duration: 3 Nov 20198 Nov 2019

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
Country/TerritoryChina
CityMacau
Period3/11/198/11/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Funding

*This work is supported by AVL Turkey and Scientific and Technological Research Council of Turkey under the grant agreement TEYDEB 1515 / 5169901 1Y. Bicer is with Faculty of Aeronautics and Astronautics, Aerospace Engineering, Istanbul Technical University, Turkey biceryu at itu.edu.tr 2A. Alizadeh is with Faculty of Mechatronics Engineering, Istanbul Technical University, Turkey Alizadeha at itu.edu.tr 3N.K. Ure is with Faculty of Aeronautics and Astronautics, Department of Aeronautical Engineering, Istanbul Technical University, Turkey ure at itu.edu.tr 4A. Erdogan and O. Kizilirmak are with AVL Turkey, Istanbul, Turkey ahmetcan.erdogan, orkun.kizilirmak at avl.com ACKNOWLEDGMENT This work is supported by Scientific and Technological Research Council of Turkey (Turkish:TÜBİTAK) under the grant agreement TEYDEB 1515 / 5169901.

FundersFunder number
AVL Turkey and Scientific and Technological Research Council of TurkeyTEYDEB 1515 / 5169901 1Y
TÜBİTAKTEYDEB 1515 / 5169901
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

    Fingerprint

    Dive into the research topics of 'Sample Efficient Interactive End-to-End Deep Learning for Self-Driving Cars with Selective Multi-Class Safe Dataset Aggregation'. Together they form a unique fingerprint.

    Cite this