No abstract

We present a new approach to integrate sensors into robot motion planning by combining the concept of the Perceptual Control Manifold (PCM) and the Topology Representing Network (TRN) algorithm. Motion planning should incorporate sensing due to the presence of uncertainty. Therefore, the PCM extends the notion of robot configuration space to include sensor space. Exploiting the topology preserving features of the TRN algorithm, the neural network learns a representation of the PCM. The learnt representation of the manifold is then used as a basis for motion planning with various constraints. The feasibility of this approach is demonstrated by experiments with a pneumatically driven robot arm (SoftAmn) .

The control of light-weight compliant robot arms is cumbersome due to the fact that their Coriolis forces are large, and the forces exerted by the relatively weak actuators may change in time as the result of external (e.g. temperature) influences. We describe and analyse the behaviour of a light-weight robot arm, the SoftArm robot. It is found that the hysteretic force-position relationship of the arm can be explained from its structure. This knowledge is used in the construction of a neural-network-based controller. Experiments show that the network is able to control the robot arm accurately after a training session of only a few minutes.

No abstract

No abstract