Abstract
Accurate classification and identification of the detected terrain is the basis for the long-distance patrol mission of the planetary rover. But terrain measurement based on vision and radar is subject to conditions such as light changes and dust storms. In this paper, under the premise of not increasing the sensor load of the existing rover, a terrain classification and recognition method based on vibration is proposed. Firstly, the time-frequency domain transformation of vibration information is realized by fast Fourier transform (FFT), and the characteristic representation of vibration information is given. Secondly, a deep neural network based on multi-layer perception is designed to realize classification of different terrains. Finally, combined with the Jackal unmanned vehicle platform, the XQ unmanned vehicle platform, and the vibration sensor, the terrain classification comparison test based on five different terrains was completed. The results show that the proposed algorithm has higher classification accuracy, and different platforms and running speeds have certain influence on the terrain classification at the same time, which provides support for subsequent practical applications.
Highlights
With the deepening of deep space exploration missions, planetary rovers have become the main mode of detecting activities [1], requiring rovers to have accurate perception of the environment
Based on the existing research, combined with the characteristics of planetary rover, this paper proposes a new three-dimensional terrain classification and recognition method based on multi-layer perception
It can be seen that the overall classification accuracy of the XQ unmanned vehicle platform has from the horizontal comparison of speed, it has a higher overall classification accuracy at a reached a very high level, and there is no uniform law on the influence of speed on its classification speed of v = 0.4 m/s, which is similar to the results of the Jackal unmanned vehicle platform
Summary
With the deepening of deep space exploration missions, planetary rovers have become the main mode of detecting activities [1], requiring rovers to have accurate perception of the environment. Weiss et al [29] realized terrain classification based on the support vector machine and analyzed the influence of different vibration measurement directions on the results, giving a simple and effective acquisition mode. The vibration sensing measurement unit of the mobile platform was used for data acquisition, and the classification process is combined with principal component analysis to extract and reduce the features, and the principal component analysis transform coefficients are used to develop and construct the manifold curve These known coefficients are used to insert unknown coefficients of the terrain as the platform motion speed changes. Based on the existing research, combined with the characteristics of planetary rover, this paper proposes a new three-dimensional terrain classification and recognition method based on multi-layer perception.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have