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

Symbolic Manipulation Planning with Discovered Object and Relational Predicates (2401.01123v1)

Published 2 Jan 2024 in cs.RO

Abstract: Discovering the symbols and rules that can be used in long-horizon planning from a robot's unsupervised exploration of its environment and continuous sensorimotor experience is a challenging task. The previous studies proposed learning symbols from single or paired object interactions and planning with these symbols. In this work, we propose a system that learns rules with discovered object and relational symbols that encode an arbitrary number of objects and the relations between them, converts those rules to Planning Domain Description Language (PDDL), and generates plans that involve affordances of the arbitrary number of objects to achieve tasks. We validated our system with box-shaped objects in different sizes and showed that the system can develop a symbolic knowledge of pick-up, carry, and place operations, taking into account object compounds in different configurations, such as boxes would be carried together with a larger box that they are placed on. We also compared our method with the state-of-the-art methods and showed that planning with the operators defined over relational symbols gives better planning performance compared to the baselines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. G. Konidaris, “On the necessity of abstraction,” Current opinion in behavioral sciences, vol. 29, pp. 1–7, 2019.
  2. G. Konidaris, L. Kaelbling, and T. Lozano-Perez, “Constructing symbolic representations for high-level planning,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 28, no. 1, 2014.
  3. G. Konidaris, L. P. Kaelbling, and T. Lozano-Perez, “From skills to symbols: Learning symbolic representations for abstract high-level planning,” Journal of Artificial Intelligence Research, vol. 61, pp. 215–289, 2018.
  4. E. Ugur and J. Piater, “Bottom-up learning of object categories, action effects and logical rules: From continuous manipulative exploration to symbolic planning,” in 2015 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2015, pp. 2627–2633.
  5. C. Aeronautiques, A. Howe, C. Knoblock, I. D. McDermott, A. Ram, M. Veloso, D. Weld, D. W. SRI, A. Barrett, D. Christianson, et al., “Pddl— the planning domain definition language,” Technical Report, Tech. Rep., 1998.
  6. M. Helmert, “The fast downward planning system,” Journal of Artificial Intelligence Research, vol. 26, pp. 191–246, 2006.
  7. J. Hoffmann, “Ff: The fast-forward planning system,” AI magazine, vol. 22, no. 3, pp. 57–57, 2001.
  8. M. Asai and A. Fukunaga, “Classical planning in deep latent space: Bridging the subsymbolic-symbolic boundary,” in Proceedings of the aaai conference on artificial intelligence, vol. 32, no. 1, 2018.
  9. M. Asai and C. Muise, “Learning neural-symbolic descriptive planning models via cube-space priors: The voyage home (to strips),” arXiv preprint arXiv:2004.12850, 2020.
  10. M. Asai, H. Kajino, A. Fukunaga, and C. Muise, “Classical planning in deep latent space,” Journal of Artificial Intelligence Research, vol. 74, pp. 1599–1686, 2022.
  11. A. Ahmetoglu, M. Y. Seker, J. Piater, E. Oztop, and E. Ugur, “Deepsym: Deep symbol generation and rule learning for planning from unsupervised robot interaction,” Journal of Artificial Intelligence Research, vol. 75, pp. 709–745, 2022.
  12. A. Ahmetoglu, E. Oztop, and E. Ugur, “Learning multi-object symbols for manipulation with attentive deep effect predictors,” arXiv preprint arXiv:2208.01021, 2022.
  13. A. Ahmetoglu, B. Celik, E. Oztop, and E. Ugur, “Discovering predictive relational object symbols with symbolic attentive layers,” arXiv preprint arXiv:2309.00889, 2023.
  14. E. Ugur, E. Şahin, and E. Oztop, “Unsupervised learning of object affordances for planning in a mobile manipulation platform,” in 2011 IEEE International Conference on Robotics and Automation.   IEEE, 2011, pp. 4312–4317.
  15. P. Zech, S. Haller, S. R. Lakani, B. Ridge, E. Ugur, and J. Piater, “Computational models of affordance in robotics: a taxonomy and systematic classification,” Adaptive Behavior, vol. 25, no. 5, pp. 235–271, 2017.
  16. T. Taniguchi, T. Nagai, T. Nakamura, N. Iwahashi, T. Ogata, and H. Asoh, “Symbol emergence in robotics: a survey,” Advanced Robotics, vol. 30, no. 11-12, pp. 706–728, 2016.
  17. S. James, B. Rosman, and G. Konidaris, “Learning portable representations for high-level planning,” in International Conference on Machine Learning.   PMLR, 2020, pp. 4682–4691.
  18. E. Ugur and J. Piater, “Refining discovered symbols with multi-step interaction experience,” in 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).   IEEE, 2015, pp. 1007–1012.
  19. S. James, B. Rosman, and G. Konidaris, “Autonomous learning of object-centric abstractions for high-level planning,” in International Conference on Learning Representations, 2021.
  20. T. Silver, R. Chitnis, J. Tenenbaum, L. P. Kaelbling, and T. Lozano-Pérez, “Learning symbolic operators for task and motion planning,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2021, pp. 3182–3189.
  21. R. Chitnis, T. Silver, J. B. Tenenbaum, T. Lozano-Perez, and L. P. Kaelbling, “Learning neuro-symbolic relational transition models for bilevel planning,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2022, pp. 4166–4173.
  22. T. Silver, A. Athalye, J. B. Tenenbaum, T. Lozano-Perez, and L. P. Kaelbling, “Learning neuro-symbolic skills for bilevel planning,” in Conference on Robot Learning (CoRL), 2022.
  23. T. Silver, R. Chitnis, N. Kumar, W. McClinton, T. Lozano-Pérez, L. Kaelbling, and J. B. Tenenbaum, “Predicate invention for bilevel planning,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 10, 2023, pp. 12 120–12 129.
  24. J. Achterhold, M. Krimmel, and J. Stueckler, “Learning temporally extended skills in continuous domains as symbolic actions for planning,” in Conference on Robot Learning.   PMLR, 2023, pp. 225–236.
  25. N. Kumar, W. McClinton, R. Chitnis, T. Silver, T. Lozano-Pérez, and L. P. Kaelbling, “Learning efficient abstract planning models that choose what to predict,” in 7th Annual Conference on Robot Learning, 2023.
  26. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  27. C. J. Maddison, A. Mnih, and Y. W. Teh, “The concrete distribution: A continuous relaxation of discrete random variables,” arXiv preprint arXiv:1611.00712, 2016.
  28. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
  29. T. Salimans and D. P. Kingma, “Weight normalization: A simple reparameterization to accelerate training of deep neural networks,” Advances in neural information processing systems, vol. 29, 2016.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Alper Ahmetoglu (10 papers)
  2. Erhan Oztop (22 papers)
  3. Emre Ugur (37 papers)
Citations (1)
View on Semantic Scholar

Summary

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

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

Tweets