A sensorimotor map: Modulating lateral interactions for anticipation and planning
Project Page for:
M. Toussaint (2006): A sensorimotor map: Modulating lateral interactions for anticipation and planning. Neural Computation 18, 1132-1155.
Abstract: Experimental studies of reasoning and planned behavior have provided evidence that nervous systems use internal models to perform predictive motor control, imagery, inference, and planning. Classical (model-free) reinforcement learning approaches omit such a model; standard sensori- motor models account for forward and backward functions of sensorimo- tor dependencies but do not provide a proper neural representation on which to realize planning. We propose a sensorimotor map to represent such an internal model. The map learns a state representation similar to self-organizing maps but is inherently coupled to sensor and motor signals. Motor activations modulate the lateral connection strengths and thereby induce anticipatory shifts of the activity peak on the sensori- motor map. This mechanism encodes a model of the change of stimuli depending on the current motor activities. The activation dynamics on the map are derived from neural field models. An additional dynamic process on the sensorimotor map (derived from dynamic programming) realizes planning and emits corresponding goal-directed motor sequences, for instance, to navigate through a maze.
Supplementary Videos:
Here are some movies that display the behavior of the sensorimotor map. Use full screen mode (lower right button) for a better display.
- Growth of the sensorimotor map, when exploring a plane:
-
Anticipatory shift of the represented position for different values of eta:
[eta=0 (no shift/anticipation)] [eta=0.2] [eta=0.3] [eta=0.5]
-
Path planning through a maze and inducing the corresponding motor sequences:
- Planning with obstacle avoidance enabled:
- Planning while also adapting the sensorimotor map to a change of the maze and thus changing plans online: