Dynamic Knowledge Graphs as Semantic Memory Model for Industrial Robots
This work addresses the problem of enabling industrial robots to learn and improve over time by providing them with a semantic memory model, which is an incremental step towards more cognitive robotic systems.
This paper proposes a semantic memory model for industrial robots that uses dynamic knowledge graphs to store processed sensory and related data. This enables robots to comprehend natural language work instructions and execute tasks deterministically, aiming to improve proficiency over time.
In this paper, we present a model for semantic memory that allows machines to collect information and experiences to become more proficient with time. Post semantic analysis of the sensory and other related data, the processed information is stored in the knowledge graph which is then used to comprehend the work instructions expressed in natural language. This imparts industrial robots cognitive behavior to execute the required tasks in a deterministic manner. The paper outlines the architecture of the system along with an implementation of the proposal.