Abstract
To investigate, how a Robot’s communication ability in terms of explanations can cultivate better trust relationships between a Robot and it’s human teammates. We opted a partial information game-playing environment, to immerse interaction between humans and a Robotic Agent. We designed our Robotic Agent as a Knowledge-Based (KB) Robotic Agent that does not play perfectly, but plays with significant expertise and approximates well enough by updating it’s belief all the time in a partially observable environment. We developed the explanation-generation mechanism on top of the game that generates meaningful explanations for the strategy of a game at a level that the human teammates appreciate and understand. The generated explanations adapt according to the game situation that can increase human’s overall understanding of the task domain. We evaluated the individual effectiveness of our KB Robotic Agent, by developing a Case Study with the partial information game Domino. In a computational experiment, our KB Robotic Agent played 10,000 game matches with other agents and exhibited a reasonable winning rate. With this victory proportion, we can conclude that our KB Robotic Agent captured and analysed all available information intelligently and forecast the possible moves of the opponents correctly.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Here task means game.
- 2.
NAOqi is the main programming framework, that runs on the robot and controls it.
- 3.
A HAND represents a set of seven tiles of a player.
- 4.
In some literature, it is considered as sensor model, that is the probability of observing E given that H is true.
- 5.
Sure means the belief computed after seeing the evidence, which is basically posterior probability because it reflects the level of belief computed in the light of the new evidence.
- 6.
By keeping track of the moves played by each player including passes and the number of tiles in other players’ HAND.
- 7.
Because it is the probability of the hypothesis given the observed evidence.
- 8.
When \(Prob(E \mid H)\) is considered as likelihood, it is seen as a function of H with E fixed. It indicates the compatibility of the evidence with the given hypothesis.
- 9.
Open ends on the board, the sizes of all other players’ HANDS, moves played by every player including passes and current belief space.
- 10.
Choose an adequate tile to play.
- 11.
Which means based on the goal state, our KB Robotic Agent tracks back to find the game state in which the decision was made. To do so, the KB Robotic Agent basically leaves a reasoning trace behind a goal tree, which makes it possible to answer questions about it’s behaviour (decision-made).
- 12.
We did not make strategies of playing the game, as a part of Static Explanations because we want that the human teammates should learn different strategies by observing the KB Robotic Agent’s way of playing (decisions).
- 13.
For example, in the game Domino, pass information of a player (which player passes it’s turn and on which tile number).
- 14.
A complete set of 28 Domino tiles in terms of the “number” of tiles that left in each player’s HAND.
References
Yagoda, R.E., Gillan, D.J.: You want me to trust a ROBOT? The development of a human-robot interaction trust scale. Int. J. Soc. Robot. 4(3), 235–248 (2012)
Dzindolet, M.T., Peterson, S.A., Pomranky, R.A., Pierce, L.G., Beck, H.P.: The role of trust in automation reliance. Int. J. Hum. Comput. Stud. 58(6), 697–718 (2003)
Lee, J.D., See, K.A.: Trust in automation: designing for appropriate reliance. Hum. Factors 46(1), 50–80 (2004)
Nothdurft, F., Minker, W.: Justification and transparency explanations in dialogue systems to maintain human-computer trust. In: Rudnicky, A., Raux, A., Lane, I., Misu, T. (eds.) Situated Dialog in Speech-Based Human-Computer Interaction. SCT, pp. 41–50. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-21834-2_4
Adams, B.D., Bruyn, L.E., Houde, S., Angelopoulos, P.A.: Trust in Automated Systems: Literature Review, 1st edn. Humansystems Incorporated, Canada (2003)
Billings, D.R., Schaefer, K.E., Chen, J.Y., Hancock, P.A.: Human-robot interaction: developing trust in robots. In: Proceedings of the Seventh Annual ACM/IEEE International Conference on Human-Robot Interaction, pp. 109–110. ACM, Boston (2012)
Nothdurft, F., Richter, F., Minker, W.: Probabilistic human-computer trust handling. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Philadelphia, U.S.A, pp. 51–59 (2014)
Nothdurft, F., Ultes, S., Minker, W.: Finding appropriate interaction strategies for proactive dialogue systems—an open quest. In: Proceedings of the 2nd European and the 5th Nordic Symposium on Multimodal Communication, pp. 73–80. Linköping University Electronic Press, Tartu (2015)
Sørmo, F., Cassens, J.: Explanation goals in case-based reasoning. In: Proceedings of the ECCBR 2004 Workshops, Number 142–04, pp. 165–174 (2004)
Xin, M., Sharlin, E.: Playing games with robots-a method for evaluating human-robot interaction. In: Human Robot Interaction, p. 522. Itech Education and Publishing, Vienna (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Javaid, M., Estivill-Castro, V., Hexel, R. (2019). Knowledge-Based Robotic Agent as a Game Player. In: Nayak, A., Sharma, A. (eds) PRICAI 2019: Trends in Artificial Intelligence. PRICAI 2019. Lecture Notes in Computer Science(), vol 11672. Springer, Cham. https://doi.org/10.1007/978-3-030-29894-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-29894-4_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29893-7
Online ISBN: 978-3-030-29894-4
eBook Packages: Computer ScienceComputer Science (R0)