Generating Goal-Directed Visuomotor Plans Based on Learning Using a Predictive Coding-type Deep Visuomotor Recurrent Neural Network Model
This addresses the problem of robotic planning and generalization for researchers in robotics and AI, though it is incremental with a focus on improving generalization in visuomotor tasks.
The paper tackles generating goal-directed visuomotor plans using a predictive coding-type deep recurrent neural network, showing that the model can generalize to unlearned goal states through error minimization, but requires a large number of learning trajectories for sufficient generalization.
The current paper presents how a predictive coding type deep recurrent neural networks can generate vision-based goal-directed plans based on prior learning experience by examining experiment results using a real arm robot. The proposed deep recurrent neural network learns to predict visuo-proprioceptive sequences by extracting an adequate predictive model from various visuomotor experiences related to object-directed behaviors. The predictive model was developed in terms of mapping from intention state space to expected visuo-proprioceptive sequences space through iterative learning. Our arm robot experiments adopted with three different tasks with different levels of difficulty showed that the error minimization principle in the predictive coding framework applied to inference of the optimal intention states for given goal states can generate goal-directed plans even for unlearned goal states with generalization. It was, however, shown that sufficient generalization requires relatively large number of learning trajectories. The paper discusses possible countermeasure to overcome this problem.