GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving

TL;DR

This paper introduces GIN, a graph-based interaction-aware constraint policy optimization method for autonomous driving, enhancing safety and robustness in dynamic traffic scenarios through simultaneous training of motion prediction and control modules.

Contribution

It presents a novel graph convolution network-based framework that models social interactions and integrates motion prediction with control for safer autonomous driving.

Findings

Achieved state-of-the-art navigation performance in CARLA simulator.

Enhanced robustness of motion prediction against abnormal movements.

Demonstrated safety improvements in dynamic traffic scenarios.

Abstract

Applying reinforcement learning to autonomous driving entails particular challenges, primarily due to dynamically changing traffic flows. To address such challenges, it is necessary to quickly determine response strategies to the changing intentions of surrounding vehicles. This paper proposes a new policy optimization method for safe driving using graph-based interaction-aware constraints. In this framework, the motion prediction and control modules are trained simultaneously while sharing a latent representation that contains a social context. To reflect social interactions, we illustrate the movements of agents in graph form and filter the features with the graph convolution networks. This helps preserve the spatiotemporal locality of adjacent nodes. Furthermore, we create feedback loops to combine these two modules effectively. As a result, this approach encourages the learned controller to be safe from dynamic risks and renders the motion prediction robust to abnormal movements. In the experiment, we set up a navigation scenario comprising various situations with CARLA, an urban driving simulator. The experiments show state-of-the-art performance on navigation strategy and motion prediction compared to the baselines.