Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unsupervised, Bottom-up Category Discovery for Symbol Grounding with a Curious Robot (2404.03092v1)

Published 3 Apr 2024 in cs.CL and cs.RO

Abstract: 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

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. A generative framework for multimodal learning of spatial concepts and object categories: An unsupervised. In 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), pages 376–383. unknown, September 2017.
  2. Few-Shot continual active learning by a robot. In 36th Conference on Neural Information Processing Systems.
  3. R-IAC: Robust intrinsically motivated exploration and active learning. IEEE Trans. Auton. Ment. Dev., 1(3):155–169, October 2009.
  4. Active learning of inverse models with intrinsically motivated goal exploration in robots. Rob. Auton. Syst., 61(1):49–73, January 2013.
  5. Experience grounds language. arXiv, 2020.
  6. YOLOv4: Optimal speed and accuracy of object detection. April 2020.
  7. Jerome Bruner. Child’s Talk: Learning to Use Language. W. W. Norton & Company, 1983.
  8. Developmental robotics: From babies to robots. MIT press, 2015.
  9. RL-IAC: An exploration policy for online saliency learning on an autonomous mobile robot. In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, October 2016.
  10. On infant speech perception and the acquisition of language. In Stevan Harnad, editor, Categorical perception: The groundwork of cognition , (pp, volume 599, pages 161–195. Cambridge University Press, x, New York, NY, US, 1987.
  11. Ginsburg and Herbert Sylvia Opper. Piaget’s Theory of Intellectual Development. International Psychotherapy Institute E-Books, 3rd edition, 1988.
  12. Stevan Harnad. The symbol grounding problem. Physica D, 42(1-3):335–346, 1990.
  13. Stevan Harnad. To cognize is to categorize: Cognition is categorization. In Handbook of Categorization in Cognitive Science, pages 21–54. 2017.
  14. Mark Johnson. The meaning of the body: Aesthetics of human understanding. University of Chicago Press, 2008.
  15. The symbol grounding problem re-framed as concreteness-abstractness learned through spoken interaction. In Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Full Papers, August 2022.
  16. Simple learning and compositional application of perceptually grounded word meanings for incremental reference resolution. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 292–301, Beijing, China, 2015. Association for Computational Linguistics.
  17. rrSDS: Towards a robot-ready spoken dialogue system. In Proceedings of the 21st Annual SIGdial Meeting on Discourse and Dialogue, Virtual, 2020. Association for Computational Linguistics.
  18. Segment anything. arXiv:2304. 02643.
  19. Human-level concept learning through probabilistic program induction. Science, 350(6266):1332–1338, December 2015.
  20. CORe50: a new dataset and benchmark for continuous object recognition. In Sergey Levine, Vincent Vanhoucke, and Ken Goldberg, editors, Proceedings of the 1st Annual Conference on Robot Learning, volume 78 of Proceedings of Machine Learning Research, pages 17–26. PMLR, 2017.
  21. Active class selection for Few-Shot Class-Incremental learning. In Conference on Lifelong Learning Agents.
  22. Lorraine McCune. How Children Learn to Learn Language. Oxford University Press, 2008.
  23. ReTiCo: An open-source framework for modeling real-time conversations in spoken dialogue systems. In Tagungsband der 30. Konferenz Elektronische Sprachsignalverarbeitung 2019, ESSV, pages 134–140, Dresden, March 2019. TUDpress, Dresden.
  24. Explauto: an open-source python library to study autonomous exploration in developmental robotics. In 4th International Conference on Development and Learning and on Epigenetic Robotics. IEEE, October 2014.
  25. Quantifying children’s sensorimotor experience: Child body-object interaction ratings for 3359 english words. Behav. Res. Methods, 54(6):2864–2877, December 2022.
  26. Online active continual learning for robotic lifelong object recognition. IEEE Trans Neural Netw Learn Syst, PP, September 2023.
  27. DINOv2: Learning robust visual features without supervision, 2023.
  28. The playground experiment: Task-Independent development of a curious robot. 2005.
  29. Discovering communication. Conn. Sci., 18(2):189–206, June 2006.
  30. Intrinsic motivation systems for autonomous mental development. IEEE Trans. Evol. Comput., 11(2):265–286, April 2007.
  31. Learning transferable visual models from natural language supervision. February 2021.
  32. David Schlangen. What a situated Language-Using agent must be able to do: A Top-Down analysis. February 2023.
  33. The development of embodied cognition: Six lessons from babies. Artif. Life, (11):13–29, 2005.
  34. HMM-Based concept learning for a mobile robot. IEEE Trans. Evol. Comput., 11(2):199–212, April 2007.
  35. The latent structure of dictionaries. Top. Cogn. Sci., 8(3):625–659, July 2016.
  36. Word learning as bayesian inference. Psychol. Rev., 114(2):245–272, April 2007.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now