Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety
This work addresses the challenge of scalable and safe autonomous driving in complex urban scenarios, though it appears incremental by combining existing imitation learning with safety enhancements.
The paper tackles the problem of designing decision and planning systems for autonomous driving in urban environments by proposing a framework that uses imitation learning with a safety controller to learn driving policies from offline data, achieving high performance in realistic simulations.
The decision and planning system for autonomous driving in urban environments is hard to design. Most current methods manually design the driving policy, which can be expensive to develop and maintain at scale. Instead, with imitation learning we only need to collect data and the computer will learn and improve the driving policy automatically. However, existing imitation learning methods for autonomous driving are hardly performing well for complex urban scenarios. Moreover, the safety is not guaranteed when we use a deep neural network policy. In this paper, we proposed a framework to learn the driving policy in urban scenarios efficiently given offline connected driving data, with a safety controller incorporated to guarantee safety at test time. The experiments show that our method can achieve high performance in realistic simulations of urban driving scenarios.