3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems
Self-driving vehicles require a number of tests to prevent fatal accidents and ensure their appropriate operation in the physical world. However, conducting vehicle tests on the road is difficult because such tests are expensive and labor intensive. In this study, we used an autonomous-driving simul...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2021-03-01
|
| Series: | Complex System Modeling and Simulation |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.23919/CSMS.2021.0004 |
| _version_ | 1797986186637082624 |
|---|---|
| author | Chunmian Lin Daxin Tian Xuting Duan Jianshan Zhou |
| author_facet | Chunmian Lin Daxin Tian Xuting Duan Jianshan Zhou |
| author_sort | Chunmian Lin |
| collection | DOAJ |
| description | Self-driving vehicles require a number of tests to prevent fatal accidents and ensure their appropriate operation in the physical world. However, conducting vehicle tests on the road is difficult because such tests are expensive and labor intensive. In this study, we used an autonomous-driving simulator, and investigated the three-dimensional environmental perception problem of the simulated system. Using the open-source CARLA simulator, we generated a CarlaSim from unreal traffic scenarios, comprising 15 000 camera-LiDAR (Light Detection and Ranging) samples with annotations and calibration files. Then, we developed Multi-Sensor Fusion Perception (MSFP) model for consuming two-modal data and detecting objects in the scenes. Furthermore, we conducted experiments on the KITTI and CarlaSim datasets; the results demonstrated the effectiveness of our proposed methods in terms of perception accuracy, inference efficiency, and generalization performance. The results of this study will faciliate the future development of autonomous-driving simulated tests. |
| first_indexed | 2024-04-11T07:30:04Z |
| format | Article |
| id | doaj.art-b479cf3e6f594c0daf6466a408d63606 |
| institution | Directory Open Access Journal |
| issn | 2096-9929 |
| language | English |
| last_indexed | 2024-04-11T07:30:04Z |
| publishDate | 2021-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Complex System Modeling and Simulation |
| spelling | doaj.art-b479cf3e6f594c0daf6466a408d636062022-12-22T04:36:56ZengTsinghua University PressComplex System Modeling and Simulation2096-99292021-03-0111455410.23919/CSMS.2021.00043D Environmental Perception Modeling in the Simulated Autonomous-Driving SystemsChunmian Lin0Daxin Tian1Xuting Duan2Jianshan Zhou3<institution>School of Transportation Science and Engineering, Beihang University</institution>, <city>Beijing</city> <postal-code>100191</postal-code>, <country>China</country><institution>School of Transportation Science and Engineering, Beihang University</institution>, <city>Beijing</city> <postal-code>100191</postal-code>, <country>China</country><institution>School of Transportation Science and Engineering, Beihang University</institution>, <city>Beijing</city> <postal-code>100191</postal-code>, <country>China</country><institution>School of Transportation Science and Engineering, Beihang University</institution>, <city>Beijing</city> <postal-code>100191</postal-code>, <country>China</country>Self-driving vehicles require a number of tests to prevent fatal accidents and ensure their appropriate operation in the physical world. However, conducting vehicle tests on the road is difficult because such tests are expensive and labor intensive. In this study, we used an autonomous-driving simulator, and investigated the three-dimensional environmental perception problem of the simulated system. Using the open-source CARLA simulator, we generated a CarlaSim from unreal traffic scenarios, comprising 15 000 camera-LiDAR (Light Detection and Ranging) samples with annotations and calibration files. Then, we developed Multi-Sensor Fusion Perception (MSFP) model for consuming two-modal data and detecting objects in the scenes. Furthermore, we conducted experiments on the KITTI and CarlaSim datasets; the results demonstrated the effectiveness of our proposed methods in terms of perception accuracy, inference efficiency, and generalization performance. The results of this study will faciliate the future development of autonomous-driving simulated tests.https://www.sciopen.com/article/10.23919/CSMS.2021.0004autonomous-driving systemenvironmental perceptionsimulated testdeep-learning model |
| spellingShingle | Chunmian Lin Daxin Tian Xuting Duan Jianshan Zhou 3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems Complex System Modeling and Simulation autonomous-driving system environmental perception simulated test deep-learning model |
| title | 3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems |
| title_full | 3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems |
| title_fullStr | 3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems |
| title_full_unstemmed | 3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems |
| title_short | 3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems |
| title_sort | 3d environmental perception modeling in the simulated autonomous driving systems |
| topic | autonomous-driving system environmental perception simulated test deep-learning model |
| url | https://www.sciopen.com/article/10.23919/CSMS.2021.0004 |
| work_keys_str_mv | AT chunmianlin 3denvironmentalperceptionmodelinginthesimulatedautonomousdrivingsystems AT daxintian 3denvironmentalperceptionmodelinginthesimulatedautonomousdrivingsystems AT xutingduan 3denvironmentalperceptionmodelinginthesimulatedautonomousdrivingsystems AT jianshanzhou 3denvironmentalperceptionmodelinginthesimulatedautonomousdrivingsystems |