Quantitative Analysis of the Impact of Baidu Apollo Parameterization on Trajectory Planning in a Critical Scenario

Hexuan Li; Francesco De Cristofaro; Faris Orucevic; Zhengguo GU; Arno Eichberger

Quantitative Analysis of the Impact of Baidu Apollo Parameterization on Trajectory Planning in a Critical Scenario

Hexuan Li, Francesco De Cristofaro, Faris Orucevic, Zhengguo GU, Arno Eichberger

Institute of Automotive Engineering (3310)

Research output: Contribution to conference › Poster › peer-review

Abstract

The increasing demand for reliable and safe high-driving automation algorithms in Autonomous Driving (AD) vehicles has driven significant advancements in the industry. This paper investigates the performance of a specific AD vehicle architecture in a critical lane change maneuver, extracted from the HighD Dataset, which consists of naturalistic vehicle trajectories recorded on German highways. The analysis focuses on different parameter configurations to understand their influence on the results. The selected AD algorithm is based on the Apollo Open Autonomous Driving Platform (AOADP). Simulation results demonstrate the significant impact of path planning algorithm parameters on lane change execution. The comparison between human driving behavior and AD systems plays a crucial role in determining sensing technology specifications. This approach provides a quantitative analysis of the impact on autonomous driving measurements, contributing to the safe specification of AD functions. These findings lay the foundation for future evaluations and improvements in the selected AD architecture.

Original language	English
Publication status	Published - 27 Dec 2023
Event	International Conference - The Science and Development of Transport: ZIRP 2023 - Zagreb, Croatia Duration: 7 Dec 2023 → 8 Dec 2023

Conference

Conference	International Conference - The Science and Development of Transport
Country/Territory	Croatia
City	Zagreb
Period	7/12/23 → 8/12/23

Keywords

Apollo Autonomous Driving Platform
Lane change path planning
Simulation

ASJC Scopus subject areas

Automotive Engineering

21_FFG_InVADE - Integrated Vehicle-in-the-Loop for Automated Driving and E-mobility
Fellendorf, M., Tomasch, E. & Eichberger, A.
1/10/21 → 30/09/24
Project: Research project
DVS: Vehicle Dynamics
Koglbauer, I. V., Lex, C., Shao, L., Semmer, M., Rogic, B., Peer, M., Hackl, A., Sternat, A. S., Schabauer, M., Samiee, S., Eichberger, A., Ager, M., Malić, D., Wohlfahrter, H., Scherndl, C., Magosi, Z. F., Orucevic, F., Puščul, D., Arefnezhad, S., Karoshi, P., Schöttel, C. E., Pandurevic, A., Harcevic, A., Wellershaus, C., Li, H., Mihalj, T., Kanuric, T., Gu, Z., Wallner, D., De Cristofaro, F., Soboleva, K., Nalic, D., Bernsteiner, S., Kraus, H., Zhao, Y., Bodner, J., Bui, D. T., Hirschberg, W., Plöckinger, M. & Khoshnood Sarabi, N.
1/01/11 → …
Project: Research area

Cite this

@conference{d1c7870616254073aa5156cc5ef9cd91,

title = "Quantitative Analysis of the Impact of Baidu Apollo Parameterization on Trajectory Planning in a Critical Scenario",

abstract = "The increasing demand for reliable and safe high-driving automation algorithms in Autonomous Driving (AD) vehicles has driven significant advancements in the industry. This paper investigates the performance of a specific AD vehicle architecture in a critical lane change maneuver, extracted from the HighD Dataset, which consists of naturalistic vehicle trajectories recorded on German highways. The analysis focuses on different parameter configurations to understand their influence on the results. The selected AD algorithm is based on the Apollo Open Autonomous Driving Platform (AOADP). Simulation results demonstrate the significant impact of path planning algorithm parameters on lane change execution. The comparison between human driving behavior and AD systems plays a crucial role in determining sensing technology specifications. This approach provides a quantitative analysis of the impact on autonomous driving measurements, contributing to the safe specification of AD functions. These findings lay the foundation for future evaluations and improvements in the selected AD architecture. ",

keywords = "Apollo Autonomous Driving Platform, Lane change path planning, Simulation",

author = "Hexuan Li and {De Cristofaro}, Francesco and Faris Orucevic and Zhengguo GU and Arno Eichberger",

year = "2023",

month = dec,

day = "27",

language = "English",

note = "International Conference - The Science and Development of Transport : ZIRP 2023 ; Conference date: 07-12-2023 Through 08-12-2023",

}

TY - CONF

T1 - Quantitative Analysis of the Impact of Baidu Apollo Parameterization on Trajectory Planning in a Critical Scenario

AU - Li, Hexuan

AU - De Cristofaro, Francesco

AU - Orucevic, Faris

AU - GU, Zhengguo

AU - Eichberger, Arno

PY - 2023/12/27

Y1 - 2023/12/27

N2 - The increasing demand for reliable and safe high-driving automation algorithms in Autonomous Driving (AD) vehicles has driven significant advancements in the industry. This paper investigates the performance of a specific AD vehicle architecture in a critical lane change maneuver, extracted from the HighD Dataset, which consists of naturalistic vehicle trajectories recorded on German highways. The analysis focuses on different parameter configurations to understand their influence on the results. The selected AD algorithm is based on the Apollo Open Autonomous Driving Platform (AOADP). Simulation results demonstrate the significant impact of path planning algorithm parameters on lane change execution. The comparison between human driving behavior and AD systems plays a crucial role in determining sensing technology specifications. This approach provides a quantitative analysis of the impact on autonomous driving measurements, contributing to the safe specification of AD functions. These findings lay the foundation for future evaluations and improvements in the selected AD architecture.

AB - The increasing demand for reliable and safe high-driving automation algorithms in Autonomous Driving (AD) vehicles has driven significant advancements in the industry. This paper investigates the performance of a specific AD vehicle architecture in a critical lane change maneuver, extracted from the HighD Dataset, which consists of naturalistic vehicle trajectories recorded on German highways. The analysis focuses on different parameter configurations to understand their influence on the results. The selected AD algorithm is based on the Apollo Open Autonomous Driving Platform (AOADP). Simulation results demonstrate the significant impact of path planning algorithm parameters on lane change execution. The comparison between human driving behavior and AD systems plays a crucial role in determining sensing technology specifications. This approach provides a quantitative analysis of the impact on autonomous driving measurements, contributing to the safe specification of AD functions. These findings lay the foundation for future evaluations and improvements in the selected AD architecture.

KW - Apollo Autonomous Driving Platform

KW - Lane change path planning

KW - Simulation

M3 - Poster

T2 - International Conference - The Science and Development of Transport

Y2 - 7 December 2023 through 8 December 2023

ER -

Quantitative Analysis of the Impact of Baidu Apollo Parameterization on Trajectory Planning in a Critical Scenario

Abstract

Conference

Keywords

ASJC Scopus subject areas

Fingerprint

Projects

21_FFG_InVADE - Integrated Vehicle-in-the-Loop for Automated Driving and E-mobility

DVS: Vehicle Dynamics

Cite this