# Unsupervised, Bottom-up Category Discovery for Symbol Grounding with a Curious Robot

arXiv: https://arxiv.org/abs/2404.03092 · HTML: https://mlsanity.com/paper/2404.03092/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 3 Apr 2024.

## Builds on (most cited first, 8 of 8)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots](https://mlsanity.com/paper/1301.4862/) (2013)
- [Few-Shot Continual Active Learning by a Robot](https://mlsanity.com/paper/2210.04137/) (2022)
- [The Latent Structure of Dictionaries](https://mlsanity.com/paper/1411.0129/) (2014)
- [What A Situated Language-Using Agent Must be Able to Do: A Top-Down Analysis](https://mlsanity.com/paper/2302.08590/) (2023)

## Built on by (most cited first, 2 of 2)

- [Spontaneous emergence of linguistic statistical laws in images via artificial neural networks](https://mlsanity.com/paper/2501.18620/) (2025)
- [A Primer on Computational Semantics for Artificial Intelligence Systems](https://mlsanity.com/paper/2608.25022/) (2026)

## Abstract (arXiv)

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