Skip to Main content Skip to Navigation
Journal articles

Adaptive sensitivity decision based path planning algorithm for unmanned aerial vehicle with improved particle swarm optimization

Abstract : Automatic path planning is an essential aspect of unmanned aerial vehicle (UAV) autonomy. This paper presents a three dimensional path planning algorithm based on adaptive sensitivity decision operator combined with particle swarm optimization (PSO) technique. In the proposed method, an adaptive sensitivity decision area is constructed to overcome the defects of local optimal and slow convergence. By using this specified area, the potential particle locations with high probabilities are determined and other candidates are deleted to improve computational capacity. Then the searching space of particles is constrained in a limited boundary to avoid premature state. In addition, the searching accuracy is enhanced by the relative particle directivity from current location. The objective function is redesigned by taking into account the distance to destination and UAV self-constraints. To evaluate the path length, the paired-sample T-Test is performed and the straight line rate (SLR ) index is introduced. In the two scenarios applied in this paper, our proposed method is 35.4%35.4%, 21.6%21.6% and 49.5%49.5% better compared with other three tested optimization algorithms in the path cost on average. Correspondingly it is 9.6%9.6%, 12.8%12.8%, and 25.3%25.3% better in SLR, which is capable of generating higher quality paths efficiently for UAVs.
Document type :
Journal articles
Complete list of metadatas

https://hal-enac.archives-ouvertes.fr/hal-01364792
Contributor : Laurence Porte <>
Submitted on : Monday, September 12, 2016 - 8:14:58 PM
Last modification on : Thursday, March 5, 2020 - 5:57:31 PM

Identifiers

Citation

Liu Yang, Xuejun Zhang, Xiangmin Guan, Daniel Delahaye. Adaptive sensitivity decision based path planning algorithm for unmanned aerial vehicle with improved particle swarm optimization. Aerospace Science and Technology, Elsevier, 2016, 58, pp. 92-102. ⟨10.1016/j.ast.2016.08.017⟩. ⟨hal-01364792⟩

Share

Metrics

Record views

376