Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Comparison between Behavior Trees and Finite State Machines (2405.16137v1)

Published 25 May 2024 in cs.RO

Abstract: Behavior Trees (BTs) were first conceived in the computer games industry as a tool to model agent behavior, but they received interest also in the robotics community as an alternative policy design to Finite State Machines (FSMs). The advantages of BTs over FSMs had been highlighted in many works, but there is no thorough practical comparison of the two designs. Such a comparison is particularly relevant in the robotic industry, where FSMs have been the state-of-the-art policy representation for robot control for many years. In this work we shed light on this matter by comparing how BTs and FSMs behave when controlling a robot in a mobile manipulation task. The comparison is made in terms of reactivity, modularity, readability, and design. We propose metrics for each of these properties, being aware that while some are tangible and objective, others are more subjective and implementation dependent. The practical comparison is performed in a simulation environment with validation on a real robot. We find that although the robot's behavior during task solving is independent on the policy representation, maintaining a BT rather than an FSM becomes easier as the task increases in complexity.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. M. Iovino, E. Scukins, J. Styrud, P. Ögren, and C. Smith, “A survey of Behavior Trees in robotics and AI,” Robotics and Autonomous Systems, vol. 154, p. 104096, Aug. 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0921889022000513
  2. S. Gugliermo, D. C. Domínguez, M. Iannotta, T. Stoyanov, and E. Schaffernicht, “Evaluating behavior trees,” Robotics and Autonomous Systems, p. 104714, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0921889024000976
  3. M. Iovino, J. Förster, P. Falco, J. J. Chung, R. Siegwart, and C. Smith, “On the programming effort required to generate Behavior Trees and Finite State Machines for robotic applications,” in 2023 IEEE International Conference on Robotics and Automation (ICRA), May 2023.
  4. R. Ghzouli, T. Berger, E. B. Johnsen, S. Dragule, and A. Wąsowski, “Behavior trees in action: a study of robotics applications,” in Proceedings of the 13th ACM SIGPLAN International Conference on Software Language Engineering, 2020, pp. 196–209.
  5. F. Rovida, B. Grossmann, and V. Krüger, “Extended behavior trees for quick definition of flexible robotic tasks,” in 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp. 6793–6800.
  6. C. Paxton, A. Hundt, F. Jonathan, K. Guerin, and G. D. Hager, “Costar: Instructing collaborative robots with behavior trees and vision,” in 2017 IEEE International Conference on Robotics and Automation (ICRA), 2017, pp. 564–571.
  7. R. Balogh and D. Obdržálek, “Using Finite State Machines in Introductory Robotics,” in Robotics in Education, W. Lepuschitz, M. Merdan, G. Koppensteiner, R. Balogh, and D. Obdržálek, Eds.   Cham: Springer International Publishing, 2019, vol. 829, pp. 85–91, series Title: Advances in Intelligent Systems and Computing. [Online]. Available: http://link.springer.com/10.1007/978-3-319-97085-1_9
  8. E. W. Dijkstra, “Letters to the editor: go to statement considered harmful,” Communications of the ACM, vol. 11, no. 3, pp. 147–148, Mar. 1968. [Online]. Available: https://doi.org/10.1145/362929.362947
  9. M. Colledanchise and P. Ögren, “How Behavior Trees Modularize Hybrid Control Systems and Generalize Sequential Behavior Compositions, the Subsumption Architecture, and Decision Trees,” IEEE Transactions on Robotics, vol. 33, no. 2, pp. 372–389, Apr. 2017, kTH.
  10. O. Biggar, M. Zamani, and I. Shames, “An Expressiveness Hierarchy of Behavior Trees and Related Architectures,” IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5397–5404, Jul. 2021, conference Name: IEEE Robotics and Automation Letters.
  11. A. Klöckner, “Behavior Trees for UAV Mission Management,” INFORMATIK 2013: Informatik angepasst an Mensch, Organisation und Umwelt, vol. P-220, pp. 57–68, 2013.
  12. O. Biggar, M. Zamani, and I. Shames, “On modularity in reactive control architectures, with an application to formal verification,” arXiv:2008.12515 [cs], May 2021, arXiv: 2008.12515. [Online]. Available: http://arxiv.org/abs/2008.12515
  13. M. Olsson, “Behavior Trees for decision-making in autonomous driving,” p. 54, 2016.
  14. M. Colledanchise, R. N. Parasuraman, and P. Ogren, “Learning of Behavior Trees for Autonomous Agents,” IEEE Transactions on Games, pp. 1–1, 2018, kTH.
  15. D. Wuthier, F. Rovida, M. Fumagalli, and V. Krüger, “Productive multitasking for industrial robots,” in 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021, pp. 12 654–12 661.
  16. M. Hallen, M. Iovino, S. Sander-Tavallaey, and C. Smith, “Behavior trees in industrial applications: A case study in underground explosive charging,” arXiv preprint arXiv:2403.19602, 2024.
  17. J. M. Zutell, D. C. Conner, and P. Schillinger, “Flexible Behavior Trees: In search of the mythical HFSMBTH for Collaborative Autonomy in Robotics,” arXiv:2203.05389 [cs], Mar. 2022.
  18. D. Cáceres Domínguez, M. Iannotta, J. A. Stork, E. Schaffernicht, and T. Stoyanov, “A Stack-of-Tasks Approach Combined with Behavior Trees: A New Framework for Robot Control,” IEEE Robotics and Automation Letters, pp. 1–8, 2022.
  19. J. Bohren and S. Cousins, “The SMACH High-Level Executive [ROS News],” IEEE Robotics & Automation Magazine, vol. 17, no. 4, pp. 18–20, Dec. 2010, conference Name: IEEE Robotics & Automation Magazine.
  20. M. Iovino, J. Styrud, P. Falco, and C. Smith, “Learning Behavior Trees with Genetic Programming in Unpredictable Environments,” in 2021 IEEE International Conference on Robotics and Automation (ICRA), May 2021, pp. 4591–4597, iSSN: 2577-087X.
  21. K. French, S. Wu, T. Pan, Z. Zhou, and O. C. Jenkins, “Learning behavior trees from demonstration,” in 2019 International Conference on Robotics and Automation (ICRA).   IEEE, 2019, pp. 7791–7797.
  22. O. Gustavsson, M. Iovino, J. Styrud, and C. Smith, “Combining Context Awareness and Planning to Learn Behavior Trees from Demonstration,” in 2022 IEEE International Conference on Robot & Human Interactive Communication (RO-MAN), Aug. 2022.
  23. M. Colledanchise, D. Almeida, and P. Ögren, “Towards Blended Reactive Planning and Acting using Behavior Trees,” in 2019 International Conference on Robotics and Automation (ICRA), May 2019, pp. 8839–8845, iSSN: 2577-087X.
  24. M. Mayr, F. Ahmad, K. Chatzilygeroudis, L. Nardi, and V. Krueger, “Combining planning, reasoning and reinforcement learning to solve industrial robot tasks,” arXiv preprint arXiv:2212.03570, 2022.
  25. J. Styrud, M. Iovino, M. Norrlöf, M. Björkman, and C. Smith, “Combining Planning and Learning of Behavior Trees for Robotic Assembly,” in 2022 IEEE International Conference on Robotics and Automation (ICRA), May 2022.
  26. M. Iovino, J. Styrud, P. Falco, and C. Smith, “A framework for learning behavior trees in collaborative robotic applications,” 2023 IEEE International Conference on Automation Science and Engineering (CASE), 2023.
  27. P. Ögren, “Convergence Analysis of Hybrid Control Systems in the Form of Backward Chained Behavior Trees,” IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6073–6080, Oct. 2020, conference Name: IEEE Robotics and Automation Letters.
  28. F. Fusaro, E. Lamon, E. D. Momi, and A. Ajoudani, “A Human-Aware Method to Plan Complex Cooperative and Autonomous Tasks using Behavior Trees,” in 2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids), Jul. 2021, pp. 522–529, iSSN: 2164-0580.
  29. A. Shoulson, F. M. Garcia, M. Jones, R. Mead, and N. I. Badler, “Parameterizing Behavior Trees,” in Motion in Games, ser. Lecture Notes in Computer Science, J. M. Allbeck and P. Faloutsos, Eds.   Springer Berlin Heidelberg, 2011, pp. 144–155.
  30. E. Burke, S. Gustafson, and G. Kendall, “Diversity in genetic programming: an analysis of measures and correlation with fitness,” IEEE Transactions on Evolutionary Computation, vol. 8, no. 1, pp. 47–62, Feb. 2004, conference Name: IEEE Transactions on Evolutionary Computation.
  31. Z. Abu-Aisheh, R. Raveaux, J.-y. Ramel, and P. Martineau, “An Exact Graph Edit Distance Algorithm for Solving Pattern Recognition Problems,” in 4th International Conference on Pattern Recognition Applications and Methods 2015, Lisbon, Portugal, Jan. 2015. [Online]. Available: https://hal.archives-ouvertes.fr/hal-01168816
  32. A. A. Hagberg, D. A. Schult, and P. J. Swart, “Exploring Network Structure, Dynamics, and Function using NetworkX,” p. 5, 2008.
  33. T. Wisspeintner, T. v. d. Zant, L. Iocchi, and S. Schiffer, “RoboCup@Home: Scientific Competition and Benchmarking for Domestic Service Robots,” Interaction Studies, vol. 10, no. 3, pp. 392–426, Jan. 2009, publisher: John Benjamins. [Online]. Available: https://www.jbe-platform.com/content/journals/10.1075/is.10.3.06wis
  34. M. Breyer, J. J. Chung, L. Ott, R. Siegwart, and J. Nieto, “Volumetric grasping network: Real-time 6 dof grasp detection in clutter,” in Conference on Robot Learning.   PMLR, 2021, pp. 1602–1611.
  35. M. Iovino, “Learning behavior trees for collaborative robotics,” Ph.D. dissertation, KTH Royal Institute of Technology, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Matteo Iovino (13 papers)
  2. Julian Förster (10 papers)
  3. Pietro Falco (12 papers)
  4. Jen Jen Chung (31 papers)
  5. Roland Siegwart (236 papers)
  6. Christian Smith (27 papers)
Citations (2)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets