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

"Guess what I'm doing": Extending legibility to sequential decision tasks (2209.09141v2)

Published 19 Sep 2022 in cs.RO and cs.AI

Abstract: In this paper we investigate the notion of legibility in sequential decision tasks under uncertainty. Previous works that extend legibility to scenarios beyond robot motion either focus on deterministic settings or are computationally too expensive. Our proposed approach, dubbed PoL-MDP, is able to handle uncertainty while remaining computationally tractable. We establish the advantages of our approach against state-of-the-art approaches in several simulated scenarios of different complexity. We also showcase the use of our legible policies as demonstrations for an inverse reinforcement learning agent, establishing their superiority against the commonly used demonstrations based on the optimal policy. Finally, we assess the legibility of our computed policies through a user study where people are asked to infer the goal of a mobile robot following a legible policy by observing its actions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Would You Trust a (Faulty) Robot?: Effects of Error, Task Type and Personality on Human-Robot Cooperation and Trust. In ACM/IEEE International Conference on Human-Robot Interaction (HRI), pages 141–148, 2015. ISBN 9781450328838. doi:10.1145/2696454.2696497. URL http://dl.acm.org/citation.cfm?doid=2696454.2696497.
  2. The role of assertiveness in a storytelling game with persuasive robotic non-player characters. In Annual Symposium on Computer-Human Interaction in Play, pages 453–465, 2019.
  3. A social robot as a card game player. In Conference: Artificial Intelligence and Interactive Digital Entertainment (AIIDE), 2017.
  4. Effects of nonverbal communication on efficiency and robustness in human-robot teamwork. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2005.
  5. Effects of robot motion on human-robot collaboration. In ACM/IEEE Int. Conf. Human-Robot Interaction, pages 51–58. IEEE, 2015.
  6. Understanding robots: Making robots more legible in multi-party interactions. In 2021 30th IEEE International Conference on Robot Human Interactive Communication (RO-MAN), pages 1031–1036, 2021. doi:10.1109/RO-MAN50785.2021.9515485.
  7. Legibility and predictability of robot motion. In ACM/IEEE Int. Conf. Human-Robot Interaction, pages 301–308. IEEE, 2013.
  8. Explainable Agents and Robots: Results from a Systematic Literature Review. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), number Aamas, 2019.
  9. Encouraging human interaction with robot teams: Legible and fair subtask allocations. IEEE Robotics and Automation Letters, 7(3):6685–6692, 2022. doi:10.1109/LRA.2022.3174264.
  10. Action selection for transparent planning. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1327–1335, 2018.
  11. A. Dragan and S. Srinivasa. Generating legible motion. In Robotics: Science and Systems, 2013.
  12. Maximizing legibility in stochastic environments. In 2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN), pages 1053–1059. IEEE, 2021.
  13. A framework for sequential planning in multi-agent settings. Journal of Artificial Intelligence Research, 24:49–79, 2005.
  14. The computational complexity of probabilistic planning. J. Artificial Intelligence Res., 9:1–36, 1998.
  15. On the undecidability of probabilistic planning and infinite-horizon partially observable Markov decision problems. In Proc. 16th AAAI Conf. Artificial Intelligence, pages 541–548, 1999.
  16. A. Ng and S. Russell. Algorithms for inverse reinforcement learning. In Proc. 17th Int. Conf. Machine Learning, pages 663–670, 2000.
  17. D. Ramachandran and E. Amir. Bayesian inverse reinforcement learning. In Proc. 20th Int. Joint Conf. Artifical intelligence, pages 2586–2591, 2007.
  18. C. Papadimitriou and J. Tsitsiklis. The complexity of Markov decision processes. Mathematics of Operations Research, 12(3):441–450, 1987.
  19. Active learning for reward estimation in inverse reinforcement learning. In Proc. Eur. Conf. Machine Learning and Knowledge Discovery in Databases, pages 31–46, 2009.
  20. Karl Popper. The myth of the framework. In Rational changes in science, pages 35–62. Springer, 1976.
  21. Explicability? legibility? predictability? transparency? privacy? security? the emerging landscape of interpretable agent behavior. In Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), volume 29, pages 86–96, 2019.
  22. The need for combining implicit and explicit communication in cooperative robotic systems. page 65. Frontiers, 2018.
  23. Victoria Alonso and Paloma De La Puente. System transparency in shared autonomy: A mini review. Frontiers in Neurorobotics, 12(November):1–11, 2018. ISSN 16625218. doi:10.3389/fnbot.2018.00083.
  24. Implicit intention communication in human–robot interaction through visual behavior studies. IEEE Transactions on Human-Machine Systems, 47(4):437–448, 2017.
  25. Enabling robots to communicate their objectives. Autonomous Robots, 43(2):309–326, 2019.
  26. S. Saunderson and G. Nejat. How robots influence humans: A survey of nonverbal communication in social human–robot interaction. In Int. J. of Social Robotics, volume 11, pages 575–608. Springer, 2019.
  27. Follow me: Communicating intentions with a spherical robot. In IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN). IEEE, 2016.
  28. Anticipatory robot control for efficient human-robot collaboration. In ACM/IEEE International Conference on Human-Robot Interaction (HRI), pages 83–90. IEEE, 2016.
  29. Facilitating intention prediction for humans by optimizing robot motions. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1249–1255. IEEE, 2015.
  30. “me and you together” movement impact in multi-user collaboration tasks. In IEEE/RSJ Int. Conf. Intelligent Robots and Systems, pages 2793–2798, 2017.
  31. Learning legible motion from human–robot interactions. In Int. J. of Social Robotics, volume 9, pages 765–779. Springer, 2017.
  32. Viewpoint-based legibility optimization. In ACM/IEEE Int. Conf. Human-Robot Interaction, pages 271–278, 2016.
  33. Social momentum: A framework for legible navigation in dynamic multi-agent environments. In ACM/IEEE Int. Conf. Human-Robot Interaction, 2018.
  34. Michael Shermer. Apocalypse ai. Scientific American, 316(3):77–77, 2017.
  35. Marketing a transparent artificial intelligence (ai): A preliminary study on message design. In 18th International Marketing Trends Conference, 2019.
  36. Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai. Information fusion, 58:82–115, 2020.
  37. Machine learning interpretability: A survey on methods and metrics. Electronics, 8(8):832, 2019.
  38. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608, 2017.
  39. Explaining deep neural networks and beyond: A review of methods and applications. Proceedings of the IEEE, 109(3):247–278, 2021. doi:10.1109/JPROC.2021.3060483.
  40. Making artificial intelligence transparent: Fairness and the problem of proxy variables. Criminal Justice Ethics, 40(1):23–39, 2021.
  41. Transparency in fair machine learning: the case of explainable recommender systems. In Human and machine learning, pages 21–35. Springer, 2018.
  42. Planning and acting in partially observable stochastic domains. Artificial intelligence, 101(1-2):99–134, 1998.
  43. A unifying framework for observer-aware planning and its complexity. In Uncertainty in Artificial Intelligence, pages 610–620. PMLR, 2021.
  44. Bandit based monte-carlo planning. In European conference on machine learning, pages 282–293. Springer, 2006.
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