Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

by   Yiren Lu, et al.

Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to identify driving preferences and produce human-like behavior. However, policies based on imitation learning alone often fail to sufficiently account for safety and reliability concerns. In this paper, we show how imitation learning combined with reinforcement learning using simple rewards can substantially improve the safety and reliability of driving policies over those learned from imitation alone. In particular, we use a combination of imitation and reinforcement learning to train a policy on over 100k miles of urban driving data, and measure its effectiveness in test scenarios grouped by different levels of collision risk. To our knowledge, this is the first application of a combined imitation and reinforcement learning approach in autonomous driving that utilizes large amounts of real-world human driving data.


Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety

The decision and planning system for autonomous driving in urban environ...

A Benchmark Comparison of Imitation Learning-based Control Policies for Autonomous Racing

Autonomous racing with scaled race cars has gained increasing attention ...

Exploring the trade off between human driving imitation and safety for traffic simulation

Traffic simulation has gained a lot of interest for quantitative evaluat...

Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving

We present a training pipeline for the autonomous driving task given the...

Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving

Autonomous driving has achieved significant progress in recent years, bu...

CCIL: Context-conditioned imitation learning for urban driving

Imitation learning holds great promise for addressing the complex task o...

Please sign up or login with your details

Forgot password? Click here to reset