Heuristic and Genetic Algorithm Approaches for UAV Path Planning under Critical Situation

Abstract

The present paper applies a heuristic and genetic algorithms approaches to the path planning problem for Unmanned Aerial Vehicles (UAVs), during an emergency landing, without putting at risk people and properties. The path re-planning can be caused by critical situations such as equipment failures or extreme environmental events, which lead the current UAV mission to be aborted by executing an emergency landing. This path planning problem is introduced through a mathematical formulation, where all problem constraints are properly described. Planner algorithms must define a new path to land the UAV following problem constraints. Three path planning approaches are introduced: greedy heuristic, genetic algorithm and multi-population genetic algorithm. The greedy heuristic aims at quickly find feasible paths, while the genetic algorithms are able to return better quality solutions within a reasonable computational time. These methods are evaluated over a large set of scenarios with different levels of diffculty. Simulations are also conducted by using FlightGear simulator, where the UAV’s behaviour is evaluated for different wind velocities and wind directions. Statistical analysis reveal that combining the greedy heuristic with the genetic algorithms is a good strategy for this problem.

Online Path Generation and Navigation for Swarms of UAVs

“…The results in the ARL and LLR columns show that the RRT* algorithm [13] produced the shortest drone routes in all experiments, while RRT [15] generated the second shortest routes. The NC column shows that the proposed approach produced the safest routes in all experiments, while the greedy heuristics and GA based approach [24] produced the second safest routes. In terms of T, RRT performed the best, while the proposed approach performed second best in Experiment 2 and 3, and the greedy and GA based approach performed second best in Experiment 1 and 4.…”

“…Finally, Experiment 4 results show that the proposed approach is also suitable for complex problem instances involving high risks of drone collisions. [25], a greedy heuristics and GA based approach [24], and two sampling-based path planning algorithms called RRT [15] and RRT* [13] intensive problem that the only viable solution is a computation of the next safe states and navigation within them. Their solution supports navigation of a single vehicle.…”

“…A distinctive feature of the proposed system is its ability to foresee potential collisions and proactively find best ways to avoid the predicted collisions in order to ensure safety of the entire swarm. In contrast to the existing works [3,[6][7][8][9][11][12][13][14][15]18,19,24], our proposed system does not depend on a planning phase and produces efficient, collision-free paths in an online manner. We focus on collision prediction and avoidance and online path generation and navigation for swarms of UAVs.…”

“…LaValle [15] and Karaman and Frazzoli [13] presented sampling-based path planning algorithms. Silva Arantes et al [24] proposed a path planning approach for critical situations requiring an emergency landing of a UAV. Dong et al [9] presented a software platform for cooperative control of multiple UAVs.…”

Counterexample guided inductive optimization applied to mobile robots path planning

“…Path planning task is often modeled as an optimization problem, where a decision variable represents a given path, i.e., the sequence of points (or movements) by which the robot must move; the cost function is a certain criteria or metric whose value is optimized (e.g., distance, energy consumption, and execution time). Thus, various optimization techniques have been applied to solve path planning problems, e.g., genetic algorithm (GA) [5]- [7], A* [8], particle swarm optimization (PSO) [9], nonlinear programming (NLP) [10], and ant colony [11]. However, these optimization techniques are unable to ensure the global optimality of the robot path, although they are able to provide results sufficiently fast for on-line path planning applications.…”