Validating SuperHuman Automated Driving Performance

被引：0

作者：

Ajanovic, Zlatan ^{[1
]}

Klomp, Matthijs ^{[2
]}

Lacevic, Bakir ^{[3
]}

Shyrokau, Barys ^{[4
]}

Pretto, Paolo ^{[1
]}

Islam, Hassaan ^{[1
]}

Stettinger, Georg ^{[1
]}

Horn, Martin ^{[5
]}

机构：

[1] Virtual Vehicle Res GmbH, Graz, Austria

[2] Volvo Car Grp, Gothenburg, Sweden

[3] Univ Sarajevo, Fac Elect Engn, Sarajevo 7100, Bosnia & Herceg

[4] Delft Univ Technol, Dept Cognit Robot, Mekelweg 2, NL-2628 CD Delft, Netherlands

[5] Graz Univ Technol, Inst Automat & Control, Graz, Austria

来源：

2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) | 2020年

关键词：

automated driving; validation; lane change; multi-lane driving; traffic lights; urban driving; planning; SuperHuman; MOTION;

D O I：

10.1109/smc42975.2020.9282822

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Closed-loop validation of autonomous vehicles is an open problem, significantly influencing development and adoption of this technology. The main contribution of this paper is a novel approach to reproducible, scenario-based validation that decouples the problem into several sub-problems, while avoiding to brake the crucial couplings. First, a realistic scenario is generated from the real urban traffic. Second, human participants, drive in a virtual scenario (in a driving simulator), based on the real traffic. Third, human and automated driving trajectories are reproduced and compared in the real vehicle on an empty track without traffic. Thus, benefits of automation with respect to safety, efficiency and comfort can be clearly benchmarked in a reproducible manner. Presented approach is used to benchmark performance of SBOMP planner in one scenario and validate SuperHuman driving performance.

引用

页码：3860 / 3867

页数：8

共 50 条

[1] ASTROPHYSICS AND SUPERHUMAN PERFORMANCE
LENAT, DB
BEHAVIORAL AND BRAIN SCIENCES, 1978, 1 (01) : 109 - 110
[2] Performance enhancement: Superhuman athletes
Helen Thompson
Nature, 2012, 487 : 287 - 289
[3] Performance enhancement: Superhuman athletes
Thompson, Helen
NATURE, 2012, 487 (7407) : 287 - 289
[4] Testing and Validating High Level Components for Automated Driving: Simulation Framework for Traffic Scenarios
Zofka, Marc Rene
Klemm, Sebastian
Kuhnt, Florian
Schamm, Thomas
Zoellner, J. Marius
2016 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2016, : 144 - 150
[5] Predicting Takeover Performance in Conditionally Automated Driving
Du, Na
Zhou, Feng
Pulver, Elizabeth
Tilbury, Dawn
Robert, Lionel P.
Pradhan, Anuj K.
Yang, X. Jessie
CHI'20: EXTENDED ABSTRACTS OF THE 2020 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, 2020,
[6] Control Performance Requirements for Automated Driving Systems
Vidano, Trevor
Assadian, Francis
ELECTRONICS, 2024, 13 (05)
[7] Driving performance at lateral system limits during partially automated driving
Naujoks, Frederik
Purucker, Christian
Wiedemann, Katharina
Neukum, Alexandra
Wolter, Stefan
Steiger, Reid
ACCIDENT ANALYSIS AND PREVENTION, 2017, 108 : 147 - 162
[8] Personalizing automated driving speed to enhance user experience and performance in intermediate-level automated driving
Delmas, Maxime
Camps, Valerie
Lemercier, Celine
ACCIDENT ANALYSIS AND PREVENTION, 2024, 199
[9] Validating automated systems
Koroneos, George
Pharmaceutical Technology, 2005, 29 (03) : 42 - 54
[10] Challenges for reproducing real-life test runs in simulation for validating automated driving functions
Leitner, A.
Metzner, S.
ELEKTROTECHNIK UND INFORMATIONSTECHNIK, 2018, 135 (4-5): : 360 - 364

← 1 2 3 4 5 →