A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation
We identify the need for an easy-to-use self-driving simulator where game mechanics implicitly encourage high-quality data capture and an associated low-cost physical test platform. We design such a simulator incorporating environmental domain randomization to enhance data generalizability and a low...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/9/1112 |
| _version_ | 1797534875526365184 |
|---|---|
| author | Georgios Pappas Joshua E. Siegel Konstantinos Politopoulos Yongbin Sun |
| author_facet | Georgios Pappas Joshua E. Siegel Konstantinos Politopoulos Yongbin Sun |
| author_sort | Georgios Pappas |
| collection | DOAJ |
| description | We identify the need for an easy-to-use self-driving simulator where game mechanics implicitly encourage high-quality data capture and an associated low-cost physical test platform. We design such a simulator incorporating environmental domain randomization to enhance data generalizability and a low-cost physical test platform running the Robotic Operating System. A toolchain comprising a gamified driving simulator and low-cost vehicle platform is novel and facilitates behavior cloning and domain adaptation without specialized knowledge, supporting crowdsourced data generation. This enables small organizations to develop certain robust and resilient self-driving systems. As proof-of-concept, the simulator is used to capture lane-following data from AI-driven and human-operated agents, with these data training line following Convolutional Neural Networks that transfer without domain adaptation to work on the physical platform. |
| first_indexed | 2024-03-10T11:36:40Z |
| format | Article |
| id | doaj.art-85cff753983c4fccaabcf6cc92aaebad |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T11:36:40Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-85cff753983c4fccaabcf6cc92aaebad2023-11-21T18:49:08ZengMDPI AGElectronics2079-92922021-05-01109111210.3390/electronics10091112A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and ValidationGeorgios Pappas0Joshua E. Siegel1Konstantinos Politopoulos2Yongbin Sun3Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, GreeceDepartment of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, USADepartment of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, GreeceDepartment of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USAWe identify the need for an easy-to-use self-driving simulator where game mechanics implicitly encourage high-quality data capture and an associated low-cost physical test platform. We design such a simulator incorporating environmental domain randomization to enhance data generalizability and a low-cost physical test platform running the Robotic Operating System. A toolchain comprising a gamified driving simulator and low-cost vehicle platform is novel and facilitates behavior cloning and domain adaptation without specialized knowledge, supporting crowdsourced data generation. This enables small organizations to develop certain robust and resilient self-driving systems. As proof-of-concept, the simulator is used to capture lane-following data from AI-driven and human-operated agents, with these data training line following Convolutional Neural Networks that transfer without domain adaptation to work on the physical platform.https://www.mdpi.com/2079-9292/10/9/1112gamificationsimulationtransfer learningself-driving vehiclesautonomous systemstraining systems |
| spellingShingle | Georgios Pappas Joshua E. Siegel Konstantinos Politopoulos Yongbin Sun A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation Electronics gamification simulation transfer learning self-driving vehicles autonomous systems training systems |
| title | A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation |
| title_full | A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation |
| title_fullStr | A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation |
| title_full_unstemmed | A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation |
| title_short | A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation |
| title_sort | gamified simulator and physical platform for self driving algorithm training and validation |
| topic | gamification simulation transfer learning self-driving vehicles autonomous systems training systems |
| url | https://www.mdpi.com/2079-9292/10/9/1112 |
| work_keys_str_mv | AT georgiospappas agamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation AT joshuaesiegel agamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation AT konstantinospolitopoulos agamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation AT yongbinsun agamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation AT georgiospappas gamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation AT joshuaesiegel gamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation AT konstantinospolitopoulos gamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation AT yongbinsun gamifiedsimulatorandphysicalplatformforselfdrivingalgorithmtrainingandvalidation |