Development of A Stochastic Traffic Environment with Generative Time-Series Models for Improving Generalization Capabilities of Autonomous Driving Agents
This work addresses the generalization issue for autonomous driving agents, though it is incremental as it builds on existing RL and GAN methods.
The paper tackled the problem of simulator bias in reinforcement learning for autonomous lane changing by developing a data-driven traffic simulator using a generative adversarial network trained on real trajectory data, resulting in RL agents with stronger generalization capabilities compared to those trained on rule-based simulators.
Automated lane changing is a critical feature for advanced autonomous driving systems. In recent years, reinforcement learning (RL) algorithms trained on traffic simulators yielded successful results in computing lane changing policies that strike a balance between safety, agility and compensating for traffic uncertainty. However, many RL algorithms exhibit simulator bias and policies trained on simple simulators do not generalize well to realistic traffic scenarios. In this work, we develop a data driven traffic simulator by training a generative adverserial network (GAN) on real life trajectory data. The simulator generates randomized trajectories that resembles real life traffic interactions between vehicles, which enables training the RL agent on much richer and realistic scenarios. We demonstrate through simulations that RL agents that are trained on GAN-based traffic simulator has stronger generalization capabilities compared to RL agents trained on simple rule-driven simulators.