Interaction-aware Decision-making for Automated Vehicles using Social Value Orientation

TL;DR

This paper presents a novel framework combining Social Value Orientation with Deep Reinforcement Learning to improve decision-making in autonomous vehicles interacting with pedestrians, enabling more natural and safe driving behaviors.

Contribution

It introduces a new DRL-based decision-making framework incorporating social value orientation and a computationally-efficient pedestrian model for AVs.

Findings

The framework generates diverse driving styles.

Simulations show natural behaviors like short-stopping.

Comparative analysis of DRL algorithms demonstrates effectiveness.

Abstract

Motion control algorithms in the presence of pedestrians are critical for the development of safe and reliable Autonomous Vehicles (AVs). Traditional motion control algorithms rely on manually designed decision-making policies which neglect the mutual interactions between AVs and pedestrians. On the other hand, recent advances in Deep Reinforcement Learning allow for the automatic learning of policies without manual designs. To tackle the problem of decision-making in the presence of pedestrians, the authors introduce a framework based on Social Value Orientation and Deep Reinforcement Learning (DRL) that is capable of generating decision-making policies with different driving styles. The policy is trained using state-of-the-art DRL algorithms in a simulated environment. A novel computationally-efficient pedestrian model that is suitable for DRL training is also introduced. We perform experiments to validate our framework and we conduct a comparative analysis of the policies obtained with two different model-free Deep Reinforcement Learning Algorithms. Simulations results show how the developed model exhibits natural driving behaviours, such as short-stopping, to facilitate the pedestrian's crossing.