Mobile Robot Path Planning with a Non-Dominated Sorting Genetic Algorithm

Abstract

In many areas, such as mobile robots, video games and driverless vehicles, path planning has always attracted researchers’ attention. In the field of mobile robotics, the path planning problem is to plan one or more viable paths to the target location from the starting position within a given obstacle space. Evolutionary algorithms can effectively solve this problem. The non-dominated sorting genetic algorithm (NSGA-II) is currently recognized as one of the evolutionary algorithms with robust optimization capabilities and has solved various optimization problems. In this paper, NSGA-II is adopted to solve multi-objective path planning problems. Three objectives are introduced. Besides the usual selection, crossover and mutation operators, some practical operators are applied. Moreover, the parameters involved in the algorithm are studied. Additionally, another evolutionary algorithm and quality metrics are employed for examination. Comparison results demonstrate that non-dominated solutions obtained by the algorithm have good characteristics. Subsequently, the path corresponding to the knee point of non-dominated solutions is shown. The path is shorter, safer and smoother. This path can be adopted in the later decision-making process. Finally, the above research shows that the revised algorithm can effectively solve the multi-objective path planning problem in static environments.

An Approach to Multi-Objective Path Planning Optimization for Underwater Gliders

“…Using an adapted version of NSGA-II, Ref. [43] was able to optimize three objectives and study the influence of the input parameters, when applying it to mobile robots on a 2D plane, obtaining fast optimization speeds and a good convergence of solutions. Also applied to mobile robotics, Ref.…”

“…Regarding the related work previously presented, the closer approaches are [43,53]. The first one also analyses NSGA-II parameters influence in a MOPP problem, but the robot behaviour (it is not a glider) is much simpler there, and the scenario is 2D and does not include temporal variation, so building a path is not conditioned by the environment like in our case.…”

Real-Time Dynamic Path Planning of Mobile Robots: A Novel Hybrid Heuristic Optimization Algorithm

“…In [43], by combining artificial bee colony algorithm and evolutionary programming algorithm, they proposed a new path planning algorithm applied to path planning in two-dimensional static environment. In [44], they designed a non-dominated sorting genetic algorithm for multi-objective path planning in static environments. In [45], a heuristic PSO algorithm is proposed, which improves the PSO planning deficiency to a certain extent but only verifies the effectiveness of the algorithm in static environment.…”

An Improved Parallelized Multi-Objective Optimization Method for Complex Geographical Spatial Sampling: AMOSA-II

“…These direct optimization approaches mainly belong to three primary types: the gene algorithm series(such as MOGA [9], NSGA [10] and NSGA-II [11]), the evolution algorithm series(such as PAES [12] and PESA-II [13]) and the simulated annealing series (such as SMOSA [14], PSA [15] and AMOSA [16]). These methods, which can contribute to more than one optimal solution in an intelligent manner without considering weighting or restriction, are being widely applied in numerous fields, such as wireless sensor network design [33,34], routine plan [35,36], job dispatchment [37-40], engineer system configuration [41][42][43] and so on. AMOSA, which functions as one of the representative algorithms, is characterized by two unique aspects: the domination amount that exists between solutions and the archive to store optimal solutions [16].…”