Abstract:
To serve a user, an intelligent robot needs episodic memory to recall a sequence of events from past experiences. ART networks have been used to design episodic memories that incrementally learn new tasks without forgetting the old ones. However, ART-based episodic memories cannot adapt to changing environments. They cannot adapt the task episode to the workplace. If a user wants multiple services of the same kind, they must repeatedly command. This article proposes a hierarchical clustering resonance network (HCRN) that performs well on multimodal data and computes semantic relations between learned clusters to overcome these limitations. Using HCRN, a semantic relation-aware episodic memory (SR-EM) can adapt the retrieved task episode to the current working environment to intelligently complete the task. HCRN outperforms ART in multimodal data clustering simulations. Two robot simulations demonstrate the SR-EM’s efficacy.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
