PROJECT TITLE :
Fall Detection and Prevention Control Using Walking-Aid Cane Robot
An intelligent walking-aid cane robot is developed for assisting the elderly and therefore the physically challenged with walking. A motion control methodology is proposed for the cane robot based on human walking intention estimation. Moreover, the safety is investigated for both the cane robot and therefore the elderly. The fall detection and prevention ideas are proposed to guarantee the protection of the elderly whereas walking with the cane robot. But, the deficiency of the cane robot is that it can be overturned simply because of its small size and lightweight weight. Thus, a controllable universal joint is intended for adjusting the tilted angle of its stick. The stability of the cane robot throughout the fall prevention procedure can then be enhanced by controlling the tilted angle of continue an optimal position. A center of pressure (COP)-primarily based fall detection (COP-FD) technique is used to detect the chance of falling. During this technique, the user's COP is calculated in real time using an integrated force sensory system, which contains a six-axis force/torque sensor and an inshoe load sensor. When the COP reaches the boundary of the required safety space, i.e., the support polygon, it is assessed that the user goes to subside. The COP-FD methodology can be employed in varied cases of falling. But, for cases of stumbling, a fast fall detection methodology is proposed based on leg motion detection, and Dubois' fuzzy possibility theory is applied to adapt to totally different users. When the danger of falling has been detected, a fall prevention impedance control is executed considering each the interaction compliance and system stability. In the study, a control simulation platform was established to get the optimal controller parameters, and all the proposed strategies were finally verified through simulations and experiments.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here