Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach

TL;DR

This paper presents a neuro-symbolic deep reinforcement learning method for autonomous driving that enhances safety, convergence speed, and generalizability by integrating symbolic logic with DRL in real-world scenarios.

Contribution

The paper introduces DRLSL, a novel neuro-symbolic DRL framework that combines experience-based learning with symbolic reasoning to enable safe and efficient autonomous driving in real environments.

Findings

Successfully avoids unsafe actions during training and testing

Achieves faster convergence compared to traditional DRL

Shows improved generalizability to new scenarios

Abstract

The dynamic nature of driving environments and the presence of diverse road users pose significant challenges for decision-making in autonomous driving. Deep reinforcement learning (DRL) has emerged as a popular approach to tackle this problem. However, the application of existing DRL solutions is mainly confined to simulated environments due to safety concerns, impeding their deployment in real-world. To overcome this limitation, this paper introduces a novel neuro-symbolic model-free DRL approach, called DRL with Symbolic Logic (DRLSL) that combines the strengths of DRL (learning from experience) and symbolic first-order logic (knowledge-driven reasoning) to enable safe learning in real-time interactions of autonomous driving within real environments. This innovative approach provides a means to learn autonomous driving policies by actively engaging with the physical environment while ensuring safety. We have implemented the DRLSL framework in a highway driving scenario using the HighD dataset and demonstrated that our method successfully avoids unsafe actions during both the training and testing phases. Furthermore, our results indicate that DRLSL achieves faster convergence during training and exhibits better generalizability to new highway driving scenarios compared to traditional DRL methods.