A Gamified Simulator and Physical Platform for Self-Driving Algorithm Training and Validation
Name
electronics-10-01112.pdf
Size
43.83 MB
Format
Unknown
Checksum (MD5)
2754d884f75817041cc517c0f2757a05
Author(s)
Pappas, Georgios
Siegel, Joshua E.
Politopoulos, Konstantinos
Sun, Yongbin
Date Issued
May 2021
Journal
Electronics
Publisher
Multidisciplinary Digital Publishing Institute
Citation
Electronics 10 (9): 1112 (2021)
Version
Final published version
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3390/electronics10091112
