UAV online path planning based on dynamic multiobjective evolutionary algorithm

Online path planning (OPP) is the basic issue of some complex mission and is indeed a dynamic multi-objective optimization problem (DMOP). In this paper, we use an OPP scheme in the sense of model predictive control (MPC) to continuously update the environmental information for the planner. For solving the DMOP involved in the MPC-like OPP a dynamic multi-objective evolutionary algorithm based on linkage and prediction (LP-DMOEA) is proposed. Within this algorithm we selectively collect the historic Pareto sets and construct several time series to present the changing tendency of the dynamic Pareto set so as to properly guide the search process. Besides, a posterior method is introduced to select executive solution from the output of the LP-DMOEA. Experimental results show the advantage of the LP-DMOEA over restart method on three benchmark problems. The effectiveness of LP-DMOEA based OPP algorithm is also validated by the simulation results of a simple military case.

[1]  John J. Grefenstette,et al.  Genetic Algorithms for Changing Environments , 1992, PPSN.

[2]  Anawat Pongpunwattana,et al.  Evolution-based Dynamic Path Planning for Autonomous Vehicles , 2007, Innovations in Intelligent Machines.

[3]  I. Hatzakis,et al.  Topology of Anticipatory Populations for Evolutionary Dynamic Multi-Objective Optimization , 2006 .

[4]  Arnold Neumaier,et al.  Algorithm 808: ARfit—a matlab package for the estimation of parameters and eigenmodes of multivariate autoregressive models , 2001, TOMS.

[5]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[6]  Ugur Zengin,et al.  Dynamic target pursuit by UAVs in probabilistic threat exposure map , 2004 .

[7]  Qingfu Zhang,et al.  Prediction-Based Population Re-initialization for Evolutionary Dynamic Multi-objective Optimization , 2007, EMO.

[8]  Kimon P. Valavanis,et al.  Evolutionary algorithm based offline/online path planner for UAV navigation , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[9]  Kalyanmoy Deb,et al.  Dynamic multiobjective optimization problems: test cases, approximations, and applications , 2004, IEEE Transactions on Evolutionary Computation.

[10]  Rasmus K. Ursem,et al.  Multinational GAs: Multimodal Optimization Techniques in Dynamic Environments , 2000, GECCO.

[11]  Claudio Rossi,et al.  Tracking Moving Optima Using Kalman-Based Predictions , 2008, Evolutionary Computation.

[12]  Wright-Patterson Afb,et al.  UAV Cooperative Path Planning , 2000 .

[13]  David Wallace,et al.  Dynamic multi-objective optimization with evolutionary algorithms: a forward-looking approach , 2006, GECCO.

[14]  Jürgen Branke,et al.  Memory enhanced evolutionary algorithms for changing optimization problems , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[15]  Carlos M. Fonseca,et al.  Methodology to select solutions from the pareto-optimal set: a comparative study , 2007, GECCO '07.

[16]  Shengxiang Yang,et al.  Environment identification-based memory scheme for estimation of distribution algorithms in dynamic environments , 2011, Soft Comput..

[17]  Xin Yao,et al.  Population-Based Incremental Learning With Associative Memory for Dynamic Environments , 2008, IEEE Transactions on Evolutionary Computation.