Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledge

TL;DR

This paper introduces a method to improve autonomous driving agents by systematically creating and training on high-risk, unpredictable traffic scenarios in simulation, leading to more robust and safer autonomous vehicles.

Contribution

It develops a novel approach to generate risky driving scenarios in simulation and trains reinforcement learning agents with this data to enhance safety and performance.

Findings

Agents trained with risky scenarios show improved collision avoidance.

Increased robustness of autonomous agents in unpredictable traffic conditions.

Enhanced safety performance compared to baseline models.

Abstract

Simulation environments are good for learning different driving tasks like lane changing, parking or handling intersections etc. in an abstract manner. However, these simulation environments often restrict themselves to operate under conservative interaction behavior amongst different vehicles. But, as we know, real driving tasks often involve very high risk scenarios where other drivers often don't behave in the expected sense. There can be many reasons for this behavior like being tired or inexperienced. The simulation environment doesn't take this information into account while training the navigation agent. Therefore, in this study we especially focus on systematically creating these risk prone scenarios with heavy traffic and unexpected random behavior for creating better model-free learning agents. We generate multiple autonomous driving scenarios by creating new custom Markov Decision Process (MDP) environment iterations in the highway-env simulation package. The behavior policy is learnt by agents trained with the help from deep reinforcement learning models. Our behavior policy is deliberated to handle collisions and risky randomized driver behavior. We train model free learning agents with supplement information of risk prone driving scenarios and compare their performance with baseline agents. Finally, we casually measure the impact of adding these perturbations in the training process to precisely account for the performance improvement obtained from utilizing the learnings from these scenarios.