Navigation In Urban Environments Amongst Pedestrians Using Multi-Objective Deep Reinforcement Learning

TL;DR

This paper introduces a multi-objective deep reinforcement learning approach for autonomous urban navigation among pedestrians, demonstrating improved performance over single-objective methods in simulated environments.

Contribution

It presents a novel multi-objective deep Q-learning algorithm tailored for pedestrian-rich urban navigation, trained and tested in a custom CARLA simulation environment.

Findings

Multi-objective DQN outperforms single-objective DQN in urban navigation tasks.

The method effectively balances multiple navigation goals.

Evaluation in known and unknown environments shows robustness.

Abstract

Urban autonomous driving in the presence of pedestrians as vulnerable road users is still a challenging and less examined research problem. This work formulates navigation in urban environments as a multi objective reinforcement learning problem. A deep learning variant of thresholded lexicographic Q-learning is presented for autonomous navigation amongst pedestrians. The multi objective DQN agent is trained on a custom urban environment developed in CARLA simulator. The proposed method is evaluated by comparing it with a single objective DQN variant on known and unknown environments. Evaluation results show that the proposed method outperforms the single objective DQN variant with respect to all aspects.