Challenges in Autonomous Vehicle Testing and Validation

被引:352
作者
Koopman, Philip [1 ]
Wagner, Michael [2 ]
机构
[1] Carnegie Mellon Univ, Elect & Comp Engn, Pittsburgh, PA 15213 USA
[2] Edge Case Res LLC, Pittsburgh, PA USA
关键词
Vehicles - Computer software selection and evaluation - Safety testing;
D O I
10.4271/2016-01-0128
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
Software testing is all too often simply a bug hunt rather than a well-considered exercise in ensuring quality. A more methodical approach than a simple cycle of system-level test-fail-patch-test will be required to deploy safe autonomous vehicles at scale. The ISO 26262 development V process sets up a framework that ties each type of testing to a corresponding design or requirement document, but presents challenges when adapted to deal with the sorts of novel testing problems that face autonomous vehicles. This paper identifies five major challenge areas in testing according to the V model for autonomous vehicles: driver out of the loop, complex requirements, non-deterministic algorithms, inductive learning algorithms, and fail-operational systems. General solution approaches that seem promising across these different challenge areas include: phased deployment using successively relaxed operational scenarios, use of a monitor/actuator pair architecture to separate the most complex autonomy functions from simpler safety functions, and fault injection as a way to perform more efficient edge case testing. While significant challenges remain in safety-certifying the type of algorithms that provide high-level autonomy themselves, it seems within reach to instead architect the system and its accompanying design process to be able to employ existing software safety approaches.
引用
收藏
页码:15 / 24
页数:10
相关论文
共 37 条
[1]  
[Anonymous], 2011, 262622 ISO
[2]  
[Anonymous], 2011, 262623 ISO
[3]   System Safety as an Emergent Property in Composite Systems [J].
Black, Jennifer ;
Koopman, Philip .
2009 IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS & NETWORKS (DSN 2009), 2009, :369-378
[4]  
Butler, 1993, IEEE T SW ENGR, V19, P3
[5]  
Dima C., 2006, CMURITR0628
[6]   Pedestrian Detection: An Evaluation of the State of the Art [J].
Dollar, Piotr ;
Wojek, Christian ;
Schiele, Bernt ;
Perona, Pietro .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (04) :743-761
[7]  
Dosovitskiy A., 2015, CORR
[8]   Object Detection with Discriminatively Trained Part-Based Models [J].
Felzenszwalb, Pedro F. ;
Girshick, Ross B. ;
McAllester, David ;
Ramanan, Deva .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (09) :1627-1645
[9]  
Geraerts Roland, 2002, P WORKSH ALG FDN ROB, P43
[10]   Design by extrapolation: An evaluation of fault tolerant avionics [J].
Hammett, R .
IEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE, 2002, 17 (04) :17-25