Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Navigation Variable-based Multi-objective Particle Swarm Optimization for UAV Path Planning with Kinematic Constraints

Thi Thuy Ngan Duong, Duy-Nam Bui, Manh Duong Phung

TL;DR

The paper addresses UAV path planning under kinematic constraints by introducing NMOPSO, a navigation-variable-based multi-objective PSO. It defines four objectives—path length, collision avoidance, altitude, and smoothness—and uses a Denavit–Hartenberg inspired navigation representation combined with an adaptive region-based mutation to obtain a diverse Pareto front of feasible paths. Key contributions include the navigation-variable formulation, hypergrid-based leader selection in MOPSO, and experimental validation with a real UAV, showing NMOPSO outperforms several PSO variants and other metaheuristics. The approach yields multiple usable non-dominated paths suitable for different mission needs and demonstrates practicality through real-world flight tests and publicly available code.

Abstract

Path planning is essential for unmanned aerial vehicles (UAVs) as it determines the path that the UAV needs to follow to complete a task. This work addresses this problem by introducing a new algorithm called navigation variable-based multi-objective particle swarm optimization (NMOPSO). It first models path planning as an optimization problem via the definition of a set of objective functions that include optimality and safety requirements for UAV operation. The NMOPSO is then used to minimize those functions through Pareto optimal solutions. The algorithm features a new path representation based on navigation variables to include kinematic constraints and exploit the maneuverable characteristics of the UAV. It also includes an adaptive mutation mechanism to enhance the diversity of the swarm for better solutions. Comparisons with various algorithms have been carried out to benchmark the proposed approach. The results indicate that the NMOPSO performs better than not only other particle swarm optimization variants but also other state-of-the-art multi-objective and metaheuristic optimization algorithms. Experiments have also been conducted with real UAVs to confirm the validity of the approach for practical flights. The source code of the algorithm is available at https://github.com/ngandng/NMOPSO.

Navigation Variable-based Multi-objective Particle Swarm Optimization for UAV Path Planning with Kinematic Constraints

TL;DR

The paper addresses UAV path planning under kinematic constraints by introducing NMOPSO, a navigation-variable-based multi-objective PSO. It defines four objectives—path length, collision avoidance, altitude, and smoothness—and uses a Denavit–Hartenberg inspired navigation representation combined with an adaptive region-based mutation to obtain a diverse Pareto front of feasible paths. Key contributions include the navigation-variable formulation, hypergrid-based leader selection in MOPSO, and experimental validation with a real UAV, showing NMOPSO outperforms several PSO variants and other metaheuristics. The approach yields multiple usable non-dominated paths suitable for different mission needs and demonstrates practicality through real-world flight tests and publicly available code.

Abstract

Path planning is essential for unmanned aerial vehicles (UAVs) as it determines the path that the UAV needs to follow to complete a task. This work addresses this problem by introducing a new algorithm called navigation variable-based multi-objective particle swarm optimization (NMOPSO). It first models path planning as an optimization problem via the definition of a set of objective functions that include optimality and safety requirements for UAV operation. The NMOPSO is then used to minimize those functions through Pareto optimal solutions. The algorithm features a new path representation based on navigation variables to include kinematic constraints and exploit the maneuverable characteristics of the UAV. It also includes an adaptive mutation mechanism to enhance the diversity of the swarm for better solutions. Comparisons with various algorithms have been carried out to benchmark the proposed approach. The results indicate that the NMOPSO performs better than not only other particle swarm optimization variants but also other state-of-the-art multi-objective and metaheuristic optimization algorithms. Experiments have also been conducted with real UAVs to confirm the validity of the approach for practical flights. The source code of the algorithm is available at https://github.com/ngandng/NMOPSO.
Paper Structure (23 sections, 28 equations, 12 figures, 1 table, 1 algorithm)

This paper contains 23 sections, 28 equations, 12 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Problem Formulation
  3. Kinematic model and constraints
  4. Objective functions for path planning
  5. Path length
  6. Collision avoidance
  7. Flight altitude
  8. Smoothness
  9. Multi-objective optimization approach
  10. Pareto-optimal solution
  11. Muli-objective particle swarm optimization
  12. Navigation variables for particle position representation
  13. Region-based mutation
  14. Implementation of the NMOPSO for UAV path planning
  15. Results
  16. ...and 8 more sections

Figures (12)

  • Figure 1: Illustration of a flight path and its variables
  • Figure 2: Obstacle avoidance
  • Figure 3: Illustration of a hypergrid and non-dominated solutions
  • Figure 4: Illustration of variables for particle representation
  • Figure 5: 3D view of the paths generated by the NMOPSO in scenarios 1 and 4
  • ...and 7 more figures

Theorems & Definitions (3)

  • Definition 1
  • Definition 2
  • Definition 3