Incremental Semantic Mapping with Unsupervised On-line Learning
This work addresses incremental semantic mapping for robotics, but it appears incremental in nature, building on existing Self-Organizing Map techniques.
The paper tackles the problem of enabling robotic agents to incrementally build semantic maps of environments using unsupervised online learning, resulting in a method that successfully creates topological maps enriched with object information and clusters similar places without degrading prior knowledge.
This paper introduces an incremental semantic mapping approach, with on-line unsupervised learning, based on Self-Organizing Maps (SOM) for robotic agents. The method includes a mapping module, which incrementally creates a topological map of the environment, enriched with objects recognized around each topological node, and a module of places categorization, endowed with an incremental unsupervised learning SOM with on-line training. The proposed approach was tested in experiments with real-world data, in which it demonstrates promising capabilities of incremental acquisition of topological maps enriched with semantic information, and for clustering together similar places based on this information. The approach was also able to continue learning from newly visited environments without degrading the information previously learned.