×

What do you really want to do? Towards a theory of intentions for human-robot collaboration. (English) Zbl 07355090

Summary: The architecture described in this paper encodes a theory of intentions based on the key principles of non-procrastination, persistence, and automatically limiting reasoning to relevant knowledge and observations. The architecture reasons with transition diagrams of any given domain at two different resolutions, with the fine-resolution description defined as a refinement of, and hence tightly-coupled to, a coarse-resolution description. For any given goal, nonmonotonic logical reasoning with the coarse-resolution description computes an activity, i.e., a plan, comprising a sequence of abstract actions to be executed to achieve the goal. Each abstract action is implemented as a sequence of concrete actions by automatically zooming to and reasoning with the part of the fine-resolution transition diagram relevant to the current coarse-resolution transition and the goal. Each concrete action in this sequence is executed using probabilistic models of the uncertainty in sensing and actuation, and the corresponding fine-resolution outcomes are used to infer coarse-resolution observations that are added to the coarse-resolution history. The architecture’s capabilities are evaluated in the context of a simulated robot assisting humans in an office domain, on a physical robot (Baxter) manipulating tabletop objects, and on a wheeled robot (Turtlebot) moving objects to particular places or people. The experimental results indicate improvements in reliability and computational efficiency compared with an architecture that does not include the theory of intentions, and an architecture that does not include zooming for fine-resolution reasoning.

MSC:

03B42 Logics of knowledge and belief (including belief change)
68T27 Logic in artificial intelligence
68T30 Knowledge representation
68T37 Reasoning under uncertainty in the context of artificial intelligence
68T40 Artificial intelligence for robotics

Software:

REBA; GitHub
PDF BibTeX XML Cite
Full Text: DOI arXiv

References:

[1] Balai, E., Gelfond, M., Zhang, Y.: Towards Answer Set Programming with Sorts. In: International Conference on Logic Programming and Nonmonotonic Reasoning. Corunna, Spain (2013) · Zbl 1405.68042
[2] Balduccini, M., Gelfond, M.: Logic Programs with Consistency-Restoring Rules. In: AAAI Spring Symposium on Logical Formalization of Commonsense Reasoning, pp. 9-18 (2003)
[3] Baral, C., Gelfond, M.: Reasoning about intended actions. In: Proceedings of the National Conference on Artificial Intelligence, vol 20, p. 689 (2005) · Zbl 0882.68027
[4] Blount, J., Gelfond, M., Balduccini, M.: Towards a Theory of Intentional Agents. In: Knowledge Representation and Reasoning in Robotics. AAAI Spring Symp. Series, pp. 10-17 (2014)
[5] Blount, J., Gelfond, M., Balduccini, M.: A Theory of Intentions for Intelligent Agents. In: International Conference on Logic Programming and Nonmonotonic Reasoning, pp. 134-142. Springer (2015) · Zbl 1467.68191
[6] Bratman, M.: Intention, plans, and practical reason. Center for the Study of Language and Information (1987)
[7] Dannenhauer, D.; Cox, M.; Munoz-Avila, H., declarative metacognitive expectations for High-Level cognition, Adv. Cogn. Syst., 6, 231-250 (2018)
[8] Dissanayake, G.; Newman, P.; Clark, S., A Solution to the Simultaneous Localization and Map Building (SLAM) Problem, IEEE Trans. Robot. Autom., 17, 3, 229-241 (2001)
[9] Erdem, E.; Gelfond, M.; Leone, N., Applications of Answer Set Programming, AI Mag., 37, 3, 53-68 (2016)
[10] Erdem, E., Patoglu, V.: Applications of Action Languages in Cognitive Robotics. In: Correct Reasoning, pp. 229-246. Springer (2012) · Zbl 1357.68218
[11] Erdem, E.; Patoglu, V., applications of ASP in robotics, Kunstliche Intell., 32, 2-3, 143-149 (2018)
[12] Gabaldon, A.: Activity Recognition with Intended Actions. In: International Joint Conference on Artificial Intelligence (IJCAI). Pasadena, USA (2009)
[13] Gelfond, M.; Inclezan, D., Some Properties of System Descriptions of ALd, J Appl Non-Class Log, Spec Issue Equil Log Answer Set Programm, 23, 1-2, 105-120 (2013) · Zbl 1400.68207
[14] Gelfond, M., Kahl, Y.: Knowledge Representation, Reasoning, and the Design of Intelligent Agents: The Answer-Set Programming Approach. Cambridge University Press. https://books.google.co.nz/books?id=99XSAgAAQBAJ (2014)
[15] Hanheide, M.; Gobelbecker, M.; Horn, G.; Pronobis, A.; Sjoo, K.; Jensfelt, P.; Gretton, C.; Dearden, R.; Janicek, M.; Zender, H.; Kruijff, GJ; Hawes, N.; Wyatt, J., Robot Task Planning and Explanation in Open and Uncertain Worlds, Artif. Intell., 247, 119-150 (2017) · Zbl 1420.68210
[16] Kelley, R.; Tavakkoli, A.; King, C.; Ambardekar, A.; Nicolescu, M.; Nicolescu, M., Context-Based bayesian intent recognition, IEEE Trans. Auton. Ment. Dev., 4, 3, 215-225 (2012)
[17] Kelley, R., Tavakkoli, A., King, C., Nicolescu, M., Nicolescu, M., Bebis, G.: Understanding Human Intentions via Hidden Markov Models in Autonomous Mobile Robots. In: International Conference on Human-Robot Interaction (HRI). Amsterdam, Netherlands (2008)
[18] Li, X., Sridharan, M.: Move and the Robot Will Learn: Vision-Based Autonomous Learning of Object Models. In: International Conference on Advanced Robotics, pp. 1-6, Montevideo, Uruguay (2013)
[19] Mota, T., Sridharan, M.: Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning on Robots. In: Robotics Science and Systems. Freiburg, Germany (2019)
[20] Rao, A.S., Georgeff, M.P.: BDI Agents: From Theory to Practice. In: First International Conference on Multiagent Systems, pp. 312-319, San Francisco (1995)
[21] Riley, H., Sridharan, M.: Non-monotonic Logical Reasoning and Deep Learning for Explainable Visual Question Answering. In: International Conference on Human-Agent Interaction. Southampton, UK (2018)
[22] Riley, H., Sridharan, M.: Integrating Non-monotonic Logical Reasoning and Inductive Learning With Deep Learning for Explainable Visual Question Answering. Frontiers in Robotics and AI, special issue on Combining Symbolic Reasoning and Data-Driven Learning for Decision-Making. Volume 6 (2019)
[23] Saribatur, Z.G., Baral, C., Eiter, T.: Reactive Maintenance Policies over Equalized States in Dynamic Environments. In: Oliveira, E., Gama, J., Vale, Z., Lopes Cardoso, H. (eds.) Progress in Artificial Intelligence, pp. 709-723. Springer International Publishing, Cham (2017)
[24] Saribatur, Z.G., Eiter, T.: Reactive Policies with Planning for Action Languages. In: Michael, L., Kakas, A. (eds.) Logics in Artificial Intelligence, pp 463-480. Springer International Publishing (2016) · Zbl 1483.68424
[25] Software and results corresponding to the evaluation of our architecture. https://github.com/hril230/theoryofintentions/tree/master/code (2019)
[26] Sridharan, M.; Gelfond, M.; Zhang, S.; Wyatt, J., REBA: a Refinement-Based architecture for knowledge representation and reasoning in robotics, J. Artif. Intell. Res., 65, 87-180 (2019) · Zbl 1477.68300
[27] Sridharan, M., Meadows, B.: Theory of Explanations for Human-Robot Collaboration. In: AAAI Spring Symposium on Story-Enabled Intelligence. Stanford, USA (2019)
[28] Suchan, J., Bhatt, M., Walega, P., Schultz, C.: Visual Explanation by High-Level Abduction: on Answer-Set Programming Driven Reasoning about Moving Objects. In: AAAI Conference on Artificial Intelligence, pp. 1965-1972, New Orleans, USA (2018)
[29] Videos demonstrating the use of our architecture on robot platforms. https://drive.google.com/open?id=1mjVV25vFvi35Ai9N7RYFFOPNaZIUdpZ (2019)
[30] Zhang, Q., Inclezan, D.: An application of asp theories of intentions to understanding restaurant scenarios. International Workshop on Practical Aspects of Answer Set Programming (2017)
[31] Zhang, S.; Sridharan, M.; Wyatt, J., Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds, IEEE Trans. Robot., 31, 3, 699-713 (2015)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.