Navigation variable-based multi-objective particle swarm optimization for UAV path planning with kinematic constraints

2025-01-02

Neural computing & applications (Print)

AI Summary

This work addresses three-dimensional path planning for unmanned aerial vehicles (UAVs) subject to kinematic constraints. We propose a multi-objective particle swarm optimization (MOPSO) method employing navigation-variable encoding, where heading angle and curvature—dynamics-sensitive quantities—are explicitly modeled as decision variables. A parameterized trajectory representation is constructed and embedded with kinematic constraints, enabling direct generation of feasible trajectories and high-quality convergence to the Pareto front. Compared with NSGA-II and RRT*, our approach achieves a 37% improvement in path success rate and a 29% reduction in computational time in complex 3D environments. All generated trajectories strictly satisfy maximum turn-rate and acceleration constraints. Moreover, the method attains superior trade-offs among safety, trajectory smoothness, and energy efficiency.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Optimization
• Intelligent Robots: Motion and Path Planning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Problem

• Drone Path Planning
• Flight Capability Constraints
• Optimal Route

Innovation

• NMOPSO
• Drone Path Planning
• Multi-objective Optimization