유니티 실시간 엔진과 End-to-End CNN 접근법을 이용한 자율주행차 학습환경
Autonomous-Driving Vehicle Learning Environments using Unity Real-time Engine and End-to-End CNN Approach
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.
Abstract
Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.
참고문헌 (21)
- L. Meeden, "Emergent control and planning in an autonomous vehicle", 15th Annual Conference of the Cognitive Science Society (1993)
- P. Koopman, "Challenges in autonomous vehicle testing and validation", SAE International Journal of Transportation Safety, 4(1), pp.15~24 (2016)[DOI]
- E. Blana, "A survey of driving research simulators Around the World", Institute of Transport Studies, University of Leeds, ~ (1996)
- X. Pan, "Virtual to real reinforcement learning for autonomous driving", British Machine Version Conference (BMVC), pp.11.1~11.13 (2017)
- S. Hossain, "CAIAS simulator: self-driving vehicle simulator for AI research", International Conference on Intelligent Computing & Optimization, pp.187~195 (2018)
- M. Bojarski, "End to end learning for self-driving cars", ~ (2016)
- "Gazebo"[URL]
- "ROS.org"[URL]
- T. Linner, "Modeling and operating robotic environent using Gazebo", ROS, 2011, 957~962
- "Torcs, the open racing car simulator" (2015)[URL]
- A. Dosovitskiy, "CARLA : An open urban driving simulator", ~ (2017)
- S. Shah, "Airsim:High-fidelity visual and physical simulation for autonomous vehicles", Field and service robotics, pp.621~635 (2018)[DOI]
- "A self-driving car simulator built with Unity"[URL]
- V. De Luca, "Development of a virtual simulator for microanastomosis: new opportunities and challenges", International Conference on Augmented Reality, Virtual Reality and Computer Graphics, pp.65~81 (2016)
- L. Ni, "The research and application of products virtual exhibition technology base on unity 3D", Digital Technology and Application, 9, pp.36~ (2010)
- "Self-driving car simulation"[URL]
- F. Codevilla, "End-to-end driving via conditional imitation learning", 2018 IEEE International Conference on Robotics and Automation (ICRA) (2018)
- S. v. d. Walt, "The NumPy array: a structure for efficient numerical computation", Computing in Science & Engineering, 13(2), pp.22~30 (2011)[DOI]
- Traffic sign recognition using neural network on OpenCV: Toward intelligent vehicle, "driver assistance system", A. Lorsakul, 2008
- N. R. Pal, "A review on image segmentation techniques", Pattern recognition, 26(9), pp.1277~1294 (1993)[DOI]
- M. Hänggi, "Simulation and visualization of CNN dynamics", International Journal of Bifurcation and Chaos, 9(7), pp.1237~1261 (1999)[DOI]