Scene Modeling of Autonomous Vehicles Avoiding Stationary and Moving Vehicles on Narrow Roads

TL;DR

This paper introduces a comprehensive model for autonomous vehicle navigation on narrow roads, focusing on minimizing road occupancy and optimizing trajectory selection to safely and efficiently pass stationary and moving vehicles.

Contribution

It presents the novel principles of road width occupancy minimization and homology class-based trajectory optimization for complex narrow-road scenarios.

Findings

High scene pass rates achieved in simulations

Efficient and robust trajectory selection demonstrated

Flexible safety and efficiency trade-offs validated

Abstract

Navigating narrow roads with oncoming vehicles is a significant challenge that has garnered considerable public interest. These scenarios often involve sections that cannot accommodate two moving vehicles simultaneously due to the presence of stationary vehicles or limited road width. Autonomous vehicles must therefore profoundly comprehend their surroundings to identify passable areas and execute sophisticated maneuvers. To address this issue, this paper presents a comprehensive model for such an intricate scenario. The primary contribution is the principle of road width occupancy minimization, which models the narrow road problem and identifies candidate meeting gaps. Additionally, the concept of homology classes is introduced to help initialize and optimize candidate trajectories, while evaluation strategies are developed to select the optimal gap and most efficient trajectory. Qualitative and quantitative simulations demonstrate that the proposed approach, SM-NR, achieves high scene pass rates, efficient movement, and robust decisions. Experiments conducted in tiny gap scenarios and conflict scenarios reveal that the autonomous vehicle can robustly select meeting gaps and trajectories, compromising flexibly for safety while advancing bravely for efficiency.