Abstract：To tackle the complexity of robotic multiple sensor fusion, a suitable system structure is required. Most structures at present have a fusion center to deal with information from various sensors located at different points, but unfortunately they have no necessary connections between low level sensors. Consequently fusion center has more responsibility for communication and signal interpretation, which resulted in bottle neck problem. Moreover, sensors cannot help each other to improve task environment recognition efficiency. To overcome the above problems, we define the concept of smart sensor at first. Each smart sensor should have five abilities : prediction, planning, updating, communication and assimilation. Then we discuss the algorithm of a perception system which consists of several smart sensors. Finally we take active tactile and active stereo camera as an example to illustrate the principle of our new idea.
1 Gregory D,Hager.Task-Directed Sens or Fusion and Planning.Kluwer Academic Publ ishers,1990 2 Hackett J K,Shah M.Multi-sens or Fus ion:A Pers pective.in Proc IEEE Int Conf,on Robotics and Automation,Cincinnati,Ohio,1990:1324-1330 3 〔日〕森村正直,山崎弘郎主编,〔中〕黄香泉译.传感器技术.科学出版社,1988 4 Luo R C.M ulti-sensor Integration and Fusion in Intellegent Systems.IEEE Tran on Syst Man&Cyb,1989,19(5):901-931 5 李介谷等.图象处理技术.上海交通大学出版社,1987 6 蒋新松等.机器人学导论.辽宁科学技术出版社,1993 7 Koker M.Review of Multi-sens or Data Fusion Architectures and Techniques.IEEE Int Sym on Intel ligent Control,1993:261-266 8 Hugh F.Durrent-whyte,Integration,Coordination and Control of Multi-sensor Robot Systems.Kluwer Academic Publishers,1988 9 熊有伦.机器人学.机械工业出版社,1993