An Environmental Perception System to Autonomous Off-Road Navigation by using Multi-sensor Data Fusion

Abstract

Environmental perception is one of the most difficult problems on the research of off-road autonomous vehicles. This paper describes a multisensor data fusion based environmental perception system for off-road autonomous navigation. The system is composed of one camera, four laser range finders, one microwave radar, and several ultrasonic sensors. A hierarchical structure is used to organize the sensors from feature level to high fusion level. A 2D fusion map consisting six classifications is proposed to describe the surrounding environment. Dempster-Shafer evidence theory is adopted to decide the classification of each grid in the fusion map. A weighted evidence combination rule is proposed and implemented to improve the decision results under high conflicting circumstance. The experimental results show that the proposed system is reliable and is able to fulfil the requirements from off-road navigation.

The Target Vehicle Movement State Estimation Method with Radar Based on Kalman Filtering Algorithm

“…For examples, Wang Rongben from Jilin University in 2002 [1], Xiang Zhiyu from Zhejiang University in 2005 [2], Yu Chunhe from Zhejiang University in 2006 [3], Masafumi from Doshisha University in 2008 [4], J. Paul from German in 2010 [5], Mai Xinchen from Shanghai Jiao Tong University in 2011 [6], Zhao Wanli from Central South University in 2011 [7], Shen Ling from Nanjing University of Science and Technology in 2012 [8], , Yang Fei from Zhejiang University in 2012 [9], and Navlab Group from Carnegie Mellon University 2012 [10], are all making the hypothesis that the acceleration of target vehicle are constant, and then the relative distance and speed according to radar carrier can be observed. Kalman filtering is used to estimate movement states of target vehicle, including relative distance and speed according to radar carrier, with state equations based on rigid body dynamics principles.…”