Autonomous Driving in Reality with Reinforcement Learning and Image Translation
This addresses the challenge of reducing accidents and data needs for autonomous driving, but it is incremental as it builds on existing simulation-to-reality methods.
The paper tackles the problem of training autonomous driving agents in simulation for real-world deployment by proposing a reinforcement learning framework with image semantic segmentation to bridge the virtual-to-real gap, achieving adaptability to reality as demonstrated in the TORCS simulator.
Supervised learning is widely used in training autonomous driving vehicle. However, it is trained with large amount of supervised labeled data. Reinforcement learning can be trained without abundant labeled data, but we cannot train it in reality because it would involve many unpredictable accidents. Nevertheless, training an agent with good performance in virtual environment is relatively much easier. Because of the huge difference between virtual and real, how to fill the gap between virtual and real is challenging. In this paper, we proposed a novel framework of reinforcement learning with image semantic segmentation network to make the whole model adaptable to reality. The agent is trained in TORCS, a car racing simulator.