Ritter (1993) presented an extension to the above SOM approach for learning sensorimotor maps, the `parametrized self-organizing map' (PSOM). The PSOM can cope with kinematic models of redundant robot arms (Walter et al., 2000). I first describe the training phase and then the recall phase.
The PSOM assumes that the training patterns lie on a sensorimotor manifold. In training, a continuous mapping is constructed that maps a parameter space (resembling the array in the SOM) onto the sensorimotor manifold. As for the SOM, the parameter space is based on an array of nodes , and each node i has a weight vector
IRd (here, element in the sensorimotor space). A continuous mapping from
to
is achieved by a sum of basis functions
Hi(
) (one for each node i),
![]() ![]() ![]() ![]() ![]() |
(1.6) |
The recall works like a pattern completion. The completion of a vector is gained by finding the parameter
that minimizes the distance between
and the sensorimotor manifold
(
). Since
is only partially given, only the distance to the input components is evaluated,
![]() ![]() ![]() ![]() |
(1.7) |
This recall method has the advantage that it works in any direction. Thus, for example, a forward model can be changed into an inverse model by adjusting the gj values. Further, the method can be applied to redundant robot arms. Out of many possible postures, the one with the smallest distance to the manifold
(
) is chosen, and not an average as in section 1.5.5.
The PSOM algorithm can achieve a remarkable accuracy (for example, a mean deviation of 1% of the working space for a three degrees-of-freedom robot finger (Walter et al., 2000)), but also here limitations exist. First, we need to know the topology of the sensorimotor patterns. Second, the mapping
(
) requires a smooth sensorimotor manifold. Third, as in the previous approach, it is not clear how the algorithm can cope with noise dimensions.