A Connectionist Learning Control Architecture for Navigation

Part of Advances in Neural Information Processing Systems 3 (NIPS 1990)

Bibtex Metadata Paper


Jonathan R. Bachrach


A novel learning control architecture is used for navigation. A sophisti(cid:173) cated test-bed is used to simulate a cylindrical robot with a sonar belt in a planar environment. The task is short-range homing in the pres(cid:173) ence of obstacles. The robot receives no global information and assumes no comprehensive world model. Instead the robot receives only sensory information which is inherently limited. A connectionist architecture is presented which incorporates a large amount of a priori knowledge in the form of hard-wired networks, architectural constraints, and initial weights. Instead of hard-wiring static potential fields from object models, myarchi(cid:173) tecture learns sensor-based potential fields, automatically adjusting them to avoid local minima and to produce efficient homing trajectories. It does this without object models using only sensory information. This research demonstrates the use of a large modular architecture on a difficult task.