A novel efficient task-assign route planning method for AUV guidance in a dynamic cluttered environment

Abstract

Promoting the levels of autonomy facilitates the vehicle in performing long-range operations with minimum supervision. The capability of Autonomous Underwater Vehicles (AUVs) to fulfill the mission objectives is directly influenced by route planning and task assignment system performance. This paper proposes an efficient task-assign route planning model in a semi-dynamic operation network, where the location of some waypoints are changed by time in a bounded area. Two popular meta-heuristic algorithms named biogeography-based optimization (BBO) and particle swarm optimization (PSO) are adopted to provide real-time optimal solutions for task sequence selection and mission time management. To examine the performance of the method in a context of mission productivity, mission time management and vehicle safety, a series of Monte Carlo simulation trials are undertaken. The results of simulations declare that the proposed method is reliable and robust particularly in dealing with uncertainties and changes of the operation network topology; as a result, it can significantly enhance the level of vehicle's autonomy by relying on its reactive nature and capability of providing fast feasible solutions.

Path Planning Technologies for Autonomous Underwater Vehicles-A Review

“…Although the PSO has ''cross'' and ''change'' and the algorithm rules are simple, the GA has a memory function. Compared with the PSO, the advantage of the GA is that it can find the global optimal value according to the optimal value of the current search during the search process [163]. In [94] and [57], the GA algorithm is applied to AUV path planning to solve the traveling salesman problem (TSP).…”

Online path planning for AUV rendezvous in dynamic cluttered undersea environment using evolutionary algorithms

“…3) Dynamic Uncertain Obstacles: This group of objects moving self-propelled while their motion gets affected by current fields and calculated according to Eq. (18).…”

“…For the AUV path planning problem in a large-scale operation area, generating a feasible solution that satisfies time and collision constraints is more essential than providing an exact optimal solution; hence, having a quick acceptable path that satisfies all constraints is appropriate than taking a long computational time to find the best path. Meta-heuristic evolutionbased optimization algorithms are capable of being implemented on a parallel machine with multiple processors, which can speed up the computation process; hence, these methods are fast enough to satisfy time restrictions of the real-time applications [18,19]. The evolution-based strategies, on the other hand, propose robust solutions that usually correspond to the quasi-optimal solutions [20].…”

Hybrid Motion Planning Task Allocation Model for AUV’s Safe Maneuvering in a Realistic Ocean Environment

“…An evolution based AUV route planner has been developed by MahmoudZadeh et al, [24] in which the vehicle's operation is considered in a large scale static network of waypoints and two GA and PSO algorithms have been applied to solve the graph complexity of the routing problem. Subsequently, their proposed method was extended to more complex environment encountering a semi-dynamic operation network and efficiency of two other evolutionary algorithms of Biogeographybased Optimization (BBO) and PSO were tested and compared on vehicle's dynamic task assignment and routing [25]. Certainly, having a more efficient optimization approach for solving vehicle routing and path planning problems to achieve faster CPU time and competitive performance is still an open area for research.…”

“…Trade-off between managing the mission available time (T ) and mission objectives should be adaptively carried out by the graph route planner. The T℘ is calculated at the end of the trajectory according to (25) and gets compared to expected time Texp for traversing the corresponding distance of dij, in which the Texp≡ tij is determined from the Tℜ given by (16). If the T℘ exceeds the Texp, it means the local path planner spent extra time for coping any probable raised difficulty (e.g.…”