Safety-enhanced UAV Path Planning with Spherical Vector-based Particle Swarm Optimization (2104.10033v1)

Abstract: This paper presents a new algorithm named spherical vector-based particle swarm optimization (SPSO) to deal with the problem of path planning for unmanned aerial vehicles (UAVs) in complicated environments subjected to multiple threats. A cost function is first formulated to convert the path planning into an optimization problem that incorporates requirements and constraints for the feasible and safe operation of the UAV. SPSO is then used to find the optimal path that minimizes the cost function by efficiently searching the configuration space of the UAV via the correspondence between the particle position and the speed, turn angle and climb/dive angle of the UAV. To evaluate the performance of SPSO, eight benchmarking scenarios have been generated from real digital elevation model maps. The results show that the proposed SPSO outperforms not only other particle swarm optimization (PSO) variants including the classic PSO, phase angle-encoded PSO and quantum-behave PSO but also other state-of-the-art metaheuristic optimization algorithms including the genetic algorithm (GA), artificial bee colony (ABC), and differential evolution (DE) in most scenarios. In addition, experiments have been conducted to demonstrate the validity of the generated paths for real UAV operations. Source code of the algorithm can be found at https://github.com/duongpm/SPSO.

• The paper introduces SPSO, an innovative method that encodes UAV paths with spherical vectors to address complex, threat-laden environments.
• The paper demonstrates that SPSO outperforms conventional PSO and other metaheuristic algorithms by achieving faster convergence and higher solution quality.
• The paper shows SPSO’s practical appeal by reducing computational complexity and effectively incorporating UAV kinematic constraints into path planning.

Safety-Enhanced UAV Path Planning with Spherical Vector-Based Particle Swarm Optimization

This paper presents an innovative approach towards optimizing the path planning process for Unmanned Aerial Vehicles (UAVs) utilizing a novel algorithm named Spherical Vector-based Particle Swarm Optimization (SPSO). Addressing the needs of UAVs operating in complex environments with multiple threats and obstacles, the work focuses on ensuring both safety and feasibility in path planning by integrating specific UAV maneuver constraints into the optimization process.

Methodology Overview

UAV path planning is formalized as an optimization problem. The algorithm adopts a cost function that encapsulates multiple criteria: it minimizes path length while incorporating constraints such as threat avoidance, permitted turn angles, climb/dive angles, and altitude restrictions. These constraints are crucial to guarantee a collision-free and feasible path suitable for the UAV's operational parameters, including limits on fuel consumption and flight altitude.

The SPSO algorithm fundamentally differs from traditional PSO variants by encoding each UAV path as a set of spherical vectors. This transformation enables the algorithm to operate directly within the UAV's configuration space, which relates directly to the UAV's speed, turning, and climbing capability. Such an encoding enhances the exploration efficiency of the search space, potentially yielding better solutions in complex environments where conventional Cartesian space-based representations often struggle due to their limited adaptability to UAV kinematic constraints.

Numerical Results and Comparisons

Extensive simulations were conducted across eight scenarios generated from real digital elevation model (DEM) maps to validate the algorithm's efficiency. These scenarios vary in complexity, providing a comprehensive platform to evaluate SPSO's performance in comparison with conventional PSO, phase angle-encoded PSO (θ-PSO), quantum-behaved PSO (QPSO), and other metaheuristic algorithms like Genetic Algorithm (GA), Differential Evolution (DE), and Artificial Bee Colony (ABC).

SPSO showed superior performance by statistically outperforming the conventional PSO and other state-of-the-art algorithms in most scenarios. The results indicate that SPSO not only maintains a stable convergence in simpler environments but also excels in complex threat-ridden terrains by achieving higher-quality solutions. Notably, the algorithm exhibits faster convergence due to its optimized search-space representation. However, it was observed that QPSO struggles with complex environments, while GA and ABC showed variable performances heavily scenario-dependent.

Practical Implications

One significant implication of SPSO's design is that it inherently facilitates a reduction in computational complexity by incorporating UAV dynamic constraints into its spherical vector representation. This capability not only enhances real-time applicability but also broadens the scope for integrating additional constraints or requirements into the objective function. The flexibility and adaptiveness exhibited by SPSO in solving the path planning problem affirm its applicability to real-world UAV operations, as substantiated by the experimental validation with a 3DR Solo drone navigating through scenarios with pre-defined threats.

Future Work and Research Directions

The research presents opportunities for incorporating advanced UAV dynamic models into the SPSO algorithm to further enhance path planning quality. Future research might explore multi-objective optimization frameworks to manage more complex, interacting constraints without extensively modifying the cost function. Moreover, SPSO's application could be extended beyond UAVs, potentially benefiting a broader range of optimization challenges in fields demanding high adaptability and safety compliance in dynamic environments.

This paper contributes a meaningful advancement by addressing critical aspects of UAV path planning and opens new pathways for developing effective metaheuristic-based optimization techniques that emphasize both practicality and theoretical robustness within aerial robotics.