Welcome to Acta Armamentarii ! Today is Share:

Acta Armamentarii ›› 2023, Vol. 44 ›› Issue (5): 1267-1276.doi: 10.12382/bgxb.2022.0038

Previous Articles     Next Articles

Road Types Identification Method of Unmanned Tracked Vehicles Based on Fusion Features

LIU Jia1, LIU Hai’ou1,*(), CHEN Huiyan1, MAO Feihong2   

  1. 1 School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China
    2 Science and Technology on Vehicle Transmission Laboratory, China North Vehicle Research Institute, Beijing 100072, China
  • Received:2022-01-13 Online:2022-06-19
  • Contact: LIU Hai’ou

Abstract:

Unmanned tracked vehicles often navigate challenging terrain, and incorporating road types as priori information for tasks such as suspension control, automatic gear decision, and path planning can enhance their performance. However, methods based on single-class features have limitations in accuracy and environmental adaptability. To overcome this, a road-type identification method based on fusion features is proposed, combining deep image features with the statistical features of vertical acceleration in time, frequency, and power spectral density domains. Machine learning classification algorithms are used to identify the road types. Compared to using single class of features, the proposed method using fusion features enriches image features and vertical acceleration features, and improves the accuracy and environmental adaptability. The response speed of the method based on fusion features is similar to that of the image-based methods. Five machine learning classification algorithms are compared. The results show that support vector machine and random forest are the most accurate and fastest classification algorithms, achieving over 90% accuracy with a speed of 14 frames per second.

Key words: unmanned tracked vehicles, fusion features, machine learning, convolutional neural network, road types identification