Control of a medical aid mobile robot based on a fuzzy navigation.

P. Hoppenot , M. Benreguieg, H. Maaref., E. Colle. and C. Barret
IEEE Symposium on Robotics and Cybernetics, pp 388-393, july 1996.


 


Abstract: Some disabled people can't use properly their hands and legs. Artificial arms exist and it could be interesting to put them on a mobile platform to help those people to gain some autonomy. Our purpose is to develop this mobile platform and its command with special constraints. Most of the motion controls of the mobile robots are based on the classical scheme planning-navigation-piloting. The navigation function, the main part of which consists of obstacle avoidance, has to react quickly with the shortest response time. The real time constraint hardly limits the complexity of sensor data processing. The described navigator is built around fuzzy logic controllers. Besides the well-known possibility of taking into account human know-how, the approach provides several contributions : a low sensitivity to erroneous or inaccurate measures and, if the inputs of the controllers are normalised, a well to do portability on another platform. That allows a cost reduction in medical systems for disabled people. To show these advantages, the same fuzzy navigator has been implemented on two mobile robots. Their mechanical structures are close except for the size and the sensing system.