Abstract:
To effectively cope with the unexpected event of visual contamination of mobile robots, a contingency planning approach is proposed based on case-based reasoning (CBR). Firstly, a wheeled mobile robot (WMR) equipped with the chameleon-inspired visual system is described, and the negative-correlation mechanism of binocular movement is analyzed. In order to realize the detection of static contaminants in dynamic scene, an improved contaminant extraction algorithm is proposed, which combines the frame difference method and the background difference method. Then, an environment perception model with chameleon-inspired visual contamination for WMR is built through the analysis of environment perception when visual contamination occurs. A CBR-based contingency planning model of visual contamination is established, and the reasoning process of CBR for visual contamination is analyzed in detail. Finally, a contingency planning experiment for visual contamination is designed based on the robot general planning of target tracking, and the experimental results show that the tracking error is basically between ±15 pixels, which demonstrates that the tracking effect is better under the condition of visual contamination.