Comparison of Path Planning Algorithms for Autonomous Vehicle Navigation Using Satellite and Airborne LiDAR Data

2025-07-08

AI Summary

To address the challenge of autonomous path planning in unstructured environments (e.g., forests, mountainous regions), this paper proposes a weighted pixel-level 2D/3D road network construction method leveraging high-resolution satellite imagery and airborne LiDAR point clouds, coupled with an improved ant colony optimization algorithm, NIACO. A systematic evaluation is conducted on real-world geographic datasets—DeepGlobe and Hamilton—comparing NIACO against A*, Dijkstra, RRT*, and RRT-Connect across path cost, computational efficiency, and memory overhead. Results demonstrate that Dijkstra achieves superior stability and computational efficiency on dense, high-resolution road networks, outperforming all competitors; NIACO exhibits robust adaptability in topologically complex scenarios. This work establishes a reproducible benchmark evaluation framework for static navigation in complex terrains and lays foundational groundwork for dynamic environment path planning.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Motion and Path Planning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Autonomous vehicle navigation in unstructured environments, such as forests and mountainous regions, presents significant challenges due to irregular terrain and complex road conditions. This work provides a comparative evaluation of mainstream and well-established path planning algorithms applied to weighted pixel-level road networks derived from high-resolution satellite imagery and airborne LiDAR data. For 2D road-map navigation, where the weights reflect road conditions and terrain difficulty, A*, Dijkstra, RRT*, and a Novel Improved Ant Colony Optimization Algorithm (NIACO) are tested on the DeepGlobe satellite dataset. For 3D road-map path planning, 3D A*, 3D Dijkstra, RRT-Connect, and NIACO are evaluated using the Hamilton airborne LiDAR dataset, which provides detailed elevation information. All algorithms are assessed under identical start and end point conditions, focusing on path cost, computation time, and memory consumption. Results demonstrate that Dijkstra consistently offers the most stable and efficient performance in both 2D and 3D scenarios, particularly when operating on dense, pixel-level geospatial road-maps. These findings highlight the reliability of Dijkstra-based planning for static terrain navigation and establish a foundation for future research on dynamic path planning under complex environmental constraints.

Problem

• Compare path planning algorithms for autonomous vehicles in unstructured environments
• Evaluate 2D and 3D navigation using satellite and LiDAR data
• Assess performance metrics like path cost, computation time, and memory

Innovation

• Compares path planning algorithms for autonomous navigation
• Uses satellite and LiDAR data for road networks
• Evaluates 2D and 3D algorithms on specific datasets