A hierarchical distributed system is presented, which interprets 3D sc
enes through fusion of multisensory images. The recognition problem is
partitioned into a set of less complex subproblems by associating wit
h each representation level expert processing units that filter out un
reliable solutions and focus attention on promising ones. In this way,
the search space for possible solutions is limited in a distributed w
ay, as a priori knowledge about observations and constraints is used a
t multiple levels. Different instances of the same inference mechanism
are applied at each level. As a consequence, each processing unit is
able to search autonomously for a local solution in order to contribut
e to obtaining a globally consistent solution. An important characteri
stic of the system is to be easy to maintain and extend. The results r
eported have been obtained by using multisensory images of real scenes
considered in the context of an autonomous-driving application. Two e
xamples of interpretation of 3D road scenes are given. and the distrib
ution of computational load is discussed.