Control of pneumatic robot arm dynamics by a neural networkPatrick

The trajectory control of a pneumatically driven robot arm resembing a skeletal muscle system is studied. The arm dynamics have been shown to be hysteretic and signiicantly changing in time due to external innuences (Hesselroth et al., IEEE Systems, Man and Cybernetics, in press) thus requiring an adaptive controller. A highly adaptive feedback algorithm is suggested and shown to control accurately trajectory following tasks.