Unsupervised, Bottom-up Category Discovery for Symbol Grounding with a Curious Robot
This work addresses the challenge of enabling robots to learn meaningful categories from raw sensory input, which is incremental as it builds on prior curiosity-based approaches with improved sensory handling and generalization.
The paper tackles the Symbol Grounding Problem by developing an unsupervised, bottom-up method for a curious robot to autonomously discover categories from visual and action data, enabling symbolic grounding without predefined labels.
Towards addressing the Symbol Grounding Problem and motivated by early childhood language development, we leverage a robot which has been equipped with an approximate model of curiosity with particular focus on bottom-up building of unsupervised categories grounded in the physical world. That is, rather than starting with a top-down symbol (e.g., a word referring to an object) and providing meaning through the application of predetermined samples, the robot autonomously and gradually breaks up its exploration space into a series of increasingly specific unlabeled categories at which point an external expert may optionally provide a symbol association. We extend prior work by using a robot that can observe the visual world, introducing a higher dimensional sensory space, and using a more generalizable method of category building. Our experiments show that the robot learns categories based on actions and what it visually observes, and that those categories can be symbolically grounded into.https://info.arxiv.org/help/prep#comments