Here are some of my research projects
- Jan. 2013~Dec.2015 The study on the active vision SLAM based on the neocortex model in indoor environment, supported by NSFC (Grant NO. 61203338)
To address the problem that current active-mode SLAM methods have limitations on the autonomy and intelligence, a novel active-mode visual SLAM framework is proposed in this project. The study of this new framework is based on the memory-prediction theory and its related simulated neocortex model (SNM). Firstly, after the appearance image sequences of environments are acquired, the map building process is implemented by incorporating the learning ability of SNM and the appearance based mapping technology. Additionally, the relationship between the data association problem and the inference capability of SNM is explored; the data association algorithm is also proposed using Bayesian theory and machine learning method. Secondly, a behavior module is designed to improve the SNM. With this improved SNM, on the basis of the prediction ability of SNM the mechanism of the sensory-motor coordination is investigated by applying Bayesian programming and dynamic field theory. Furthermore the action selection and localization algorithms corresponding to the sensory-motor coordination are developed. Finally, mapping, localization and action selection are integrated to build a whole active-mode visual SLAM framework. For this active-mode visual SLAM, the action selection method and the performance evaluation strategy are further studied without considering any prior information. The results of this project are promising and they will theoretically and technically provide a new idea and new way for the open research issue of the active mode SLAM.