Neural force/position control in Cartesian space for a 6DOF industrial robot: concept and first results

Abstract

A novel concept of neural force/position control in Cartesian space (NFC) was developed and applied. The NFC concept for a 6DOF industrial robot with a 6DOF sensor (3/spl times/forces, 3/spl times/torques) is based on a cycle time of just 2 msec. NFC features include: (1) sensor data and trajectory input processing in Cartesian space, (2) learned mapping operations for force, kinematics, and dynamics with neural networks; (3) singularity robustness in the entire workspace; (4) automatic adjustment of desired trajectories to kinematic and dynamic constraints. NFC allows the control of 6DOF robots in defined contact with moving stiff objects and surfaces. This requires the dynamic handling of coupled force and position vectors. Results from simulations and real time experiments with a 6 joint manipulator (Siemens manutec r2) are discussed.