Nav-Q: Quantum Deep Reinforcement Learning for Collision-Free Navigation of Self-Driving Cars

TL;DR

Nav-Q introduces a quantum-supported deep reinforcement learning algorithm for collision-free navigation of self-driving cars, demonstrating improved training stability and convergence in simulation, with potential advantages from quantum computation.

Contribution

This work is the first to integrate quantum computation into DRL for self-driving car navigation, enhancing training performance without onboard quantum hardware.

Findings

Nav-Q outperforms classical DRL in training stability.

Quantum component increases model's descriptive power.

Quantum noise affects training but boosts exploration.

Abstract

The task of collision-free navigation (CFN) of self-driving cars is an NP-hard problem usually tackled using Deep Reinforcement Learning (DRL). While DRL methods have proven to be effective, their implementation requires substantial computing resources and extended training periods to develop a robust agent. On the other hand, quantum reinforcement learning has recently demonstrated faster convergence and improved stability in simple, non-real-world environments. In this work, we propose Nav-Q, the first quantum-supported DRL algorithm for CFN of self-driving cars, that leverages quantum computation for improving the training performance without the requirement for onboard quantum hardware. Nav-Q is based on the actor-critic approach, where the critic is implemented using a hybrid quantum-classical algorithm suitable for near-term quantum devices. We assess the performance of Nav-Q using the CARLA driving simulator, a de facto standard benchmark for evaluating state-of-the-art DRL methods. Our empirical evaluations showcase that Nav-Q surpasses its classical counterpart in terms of training stability and, in certain instances, with respect to the convergence rate. Furthermore, we assess Nav-Q in relation to effective dimension, unveiling that the incorporation of a quantum component results in a model with greater descriptive power compared to classical baselines. Finally, we evaluate the performance of Nav-Q using noisy quantum simulation, observing that the quantum noise deteriorates the training performances but enhances the exploratory tendencies of the agent during training.