ABSTRACT
This paper presents a novel algorithm for detecting contingent reactions to robot behavior in noisy real-world environments with naive users. Prior work has established that one way to detect contingency is by calculating a difference metric between sensor data before and after a robot probe of the environment. Our algorithm, CIRCLE (Contingency for Interactive Real-time CLassification of Engagement) provides a new approach to calculating this difference and detecting contingency, improving the running time for the difference calculation from 2.5 seconds to approximately 0.001 seconds on an 1100-sample vector, and effectively enabling real-time detection of contingent events. We show accuracy comparable to the best offline results for detecting contingency in this way (89.5% vs 91% in prior work), and demonstrate the utility of the real-time contingency detection in a field study of a survey-administering robot in a noisy open-world environment with naive users, showing that the robot can decrease the number of requests it makes (from 38 to 13) while more efficiently collecting survey responses (30% response rate rather than 26.3%).
- Steven M. Alessandri, Margaret W. Sullivan, and Michael Lewis. 1990. Violation of expectancy and frustration in early infancy. Developmental Psychology 26, 5 (1990), 738--744.Google ScholarCross Ref
- Minoru Asada, Koh Hosoda, Yasuo Kuniyoshi, Hiroshi Ishiguro, Toshio Inui, Yuichiro Yoshikawa, Masaki Ogino, and Chisato Yoshida. 2009. Cognitive Developmental Robotics: A Survey. IEEE Transactions on Autonomous Mental Development 1, 1 (2009), 12--34. Google ScholarDigital Library
- M. Asif, M. Sabeel, and Mujeeb ur-Rahman an Z. H. Khan. 2016. Waiter Robot -- Solution to Restaurant Automation. Proceedings of the 1st Student Multi Disciplinary Research Conference (MDSRC) November (2016).Google Scholar
- Ann E Bigelow and Philippe Rochat. 2006. Two-month-old Infants - Sensitivity to Social Contingency in Mother-Infant and Stranger-Infant Interaction. Infancy 9, 3 (2006), 313--325.Google ScholarCross Ref
- Nicholas J Butko and Javier R Movellan. 2010. Infomax Control of Eye Movements. IEEE Transactions on Autonomous Mental Development 2, 2 (2010), 91--107. Google ScholarDigital Library
- Richard L Canfield and Marshall M Haith. 1991. Young Infants - Visual Expectations for Symmetric and Asymmetric Stimulus Sequences. Developmental Psychology 27, 2 (1991), 198--208.Google ScholarCross Ref
- Angelo Cangelosi, Giorgio Metta, Gerhard Sagerer, Stefano Nolfi, Chrystopher Nehaniv, Kerstin Fischer, Jun Tani, Tony Belpaeme, Giulio Sandini, Francesco Nori, Luciano Fadiga, Britta Wrede, Katharina Rohlfing, Elio Tuci, Kerstin Dautenhahn, Joe Saunders, and Arne Zeschel. 2010. Integration of action and language knowledge: A roadmap for Developmental robotics. IEEE Transactions on Autonomous Mental Development 2, 3 (2010), 167--195. Google ScholarDigital Library
- Vivian Chu, Kalesha Bullard, and Andrea L. Thomaz. 2014. Multimodal real-time contingency detection for HRI. IEEE International Conference on Intelligent Robots and Systems Iros (2014), 3327--3332.Google Scholar
- Gunnar Farneb. 2003. Two-Frame Motion Estimation Based on Polynomial Expansion. Lecture Notes in Computer Science 2749, 1 (2003), 363--370. Google ScholarDigital Library
- Markus Finke, Kheng Lee Koay, Kerstin Dautenhahn, Chrystopher L. Nehaniv, Michael L. Walters, and Joe Saunders. 2005. Hey, I'm over here - How can a robot attract people's attention? Proceedings - IEEE International Workshop on Robot and Human Interactive Communication 2005 (2005), 7--12.Google Scholar
- Kevin Gold and Brian Scassellati. 2006. Learning acceptable windows of contingency. Connection Science 18, 2 (2006), 217--228.Google ScholarCross Ref
- Marcel Heerink, Ben Kröse, Vanessa Evers, and Bob Wielinga. 2010. Assessing acceptance of assistive social agent technology by older adults: The almere model. International Journal of Social Robotics 2, 4 (2010), 361--375.Google ScholarCross Ref
- P Kaewtrakulpong and R Bowden. 2001. An Improved Adaptive Background Mixture Model for Real- time Tracking with Shadow Detection. Advanced Video Based Surveillance Systems (2001), 1--5.Google Scholar
- Takayuki Kanda, Masahiro Shiomi, Zenta Miyashita, Hiroshi Ishiguro, and Norihiro Hagita. 2009. An affective guide robot in a shopping mall. Proceedings of the 4th ACM/IEEE International Conference on Human Robot Interaction - HRI '09 (2009), 173. Google ScholarDigital Library
- Takayuki Kanda, Masahiro Shiomi, Zenta Miyashita, Hiroshi Ishiguro, and Norihiro Hagita. 2010. A communication robot in a shopping mall. IEEE Transactions on Robotics 26, 5 (2010), 897--913. Google ScholarDigital Library
- Simon Keizer, Mary Ellen Foster, Zhuoran Wang, and Oliver Lemon. 2014. Machine Learning for Social Multiparty Human--Robot Interaction. ACM Transactions on Interactive Intelligent Systems 4, 3 (2014), 1--32. Google ScholarDigital Library
- Jinhan Lee, Crystal Chao, Aaron F. Bobick, and Andrea L. Thomaz. 2012. Multicue Contingency Detection. International Journal of Social Robotics 4, 2 (2012), 147--161.Google ScholarCross Ref
- MK Lee and Jodi Forlizzi. 2009. Designing adaptive robotic services. Proc. of IASDR'09 November (2009), 1--10.Google Scholar
- Timm Linder, Stefan Breuers, Bastian Leibe, and Kai O Arras. 2016. On multimodal people tracking from mobile platforms in very crowded and dynamic environments. In Robotics and Automation (ICRA), 2016 IEEE International Conference on. IEEE, 5512--5519.Google ScholarCross Ref
- Sara Ljungblad and Jirina Kotrbova. 2012. Hospital robot at work: something alien or an intelligent colleague? . . . Cooperative Work (2012), 177--186. Google ScholarDigital Library
- Javier R. Movellan. 2005. An infomax controller for real time detection of social contingency. Proceedings of 2005 4th IEEE International Conference on Development and Learning 2005 (2005), 19--24.Google ScholarCross Ref
- Steffen Muller, Sven Hellbach, Erik Schaffernicht, Antje Ober, Andrea Scheidig, and Horst Michael Gross. 2008. Whom to talk to? Estimating user interest from movement trajectories. Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN (2008), 532--538.Google ScholarCross Ref
- Aastha Nigam and Laurel D Riek. 2015. Social context perception for mobile robots. In Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on. IEEE, 3621--3627.Google ScholarCross Ref
- Shokoofeh Pourmehr, Jack Thomas, Jake Bruce, Jens Wawerla, and Richard Vaughan. 2017. Robust sensor fusion for finding HRI partners in a crowd. Proceedings - IEEE International Conference on Robotics and Automation i (2017), 3272--3278.Google ScholarCross Ref
- Satoru Satake, Takayuki Kanda, Dylan F Glas, Michita Imai, Hiroshi Ishiguro, and Norihiro Hagita. 2013. A robot that approaches pedestrians. IEEE Transactions on Robotics 29, 2 (2013), 508--524. Google ScholarDigital Library
- Chao Shi, Masahiro Shiomi, Christian Smith, Takayuki Kanda, and Hiroshi Ishiguro. 2013. A Model of Distributional Handing Interaction for a Mobile Robot. Robotics: Science and Systems (2013). http://www.diva-portal.org/smash/record. jsf?pid=diva2:631957Google Scholar
- N.M.a Su, L.S.b Liu, and A.b Lazar. 2014. Mundanely miraculous: The robot in healthcare. Proceedings of the NordiCHI 2014: The 8th Nordic Conference on Human-Computer Interaction: Fun, Fast, Foundational (2014), 391--400. Google ScholarDigital Library
- Hidenobu Sumioka, Yuichiro Yoshikawa, Masanori Morizono, and Minoru Asada. 2011. Socially Developmental Robot based on Self-Induced Contingency with Multi Latencies. Proceedings of The 3rd International Conference on Cognitive Neurodynamics (2011), 3--6.Google Scholar
- G M Tarabulsy, R Tessier, and a Kappas. 1996. Contingency detection and the contingent organization of behavior in interactions: implications for socioemotional development in infancy. Psychological Bulletin 120, 1 (1996), 25--41.Google ScholarCross Ref
- John S. Watson. 1972. Smiling, Cooing, and "The Game". Merrill-Palmer Quarterly of Behavior and Development 18, 4 (1972), 323--339. http://www.jstor.org/stable/ 23084026Google Scholar
- Mary-Anne Williams. 2012. Robot Social Intelligence. International Conference on Social Robotics 4 (2012), 45--55. Google ScholarDigital Library
- Fumitaka Yamaoka, Takayuki Kanda, Hiroshi Ishiguro, and Norihiro Hagita. 2006. How contingent should a communication robot be? Proceeding of the 1st ACM SIGCHI/SIGART Conference on Human-Robot Interaction - HRI '06 (2006), 313--320. Google ScholarDigital Library
- Zoran Zivkovic. 2004. Improved adaptive Gaussian mixture model for background subtraction. Proceedings of the 17th International Conference on Pattern Recognition 2, 2 (2004), 28--31. Google ScholarDigital Library
- Zoran Zivkovic and Ferdinand Van Der Heijden. 2006. Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters 27, 7 (2006), 773--780. Google ScholarDigital Library
Index Terms
- Detecting Contingency for HRI in Open-World Environments
Recommendations
Contingency Detection in Multi-Agent Interactions
HRI '21 Companion: Companion of the 2021 ACM/IEEE International Conference on Human-Robot InteractionContingency is the principle of interaction that governs how one partner influences another. This paper presents a formalization for multi-agent contingency detection over discrete intervals of humanagent interaction. A multi-agent virtual sandbox is ...
Vision-based contingency detection
HRI '11: Proceedings of the 6th international conference on Human-robot interactionWe present a novel method for the visual detection of a contingent response by a human to the stimulus of a robot action. Contingency is defined as a change in an agent's behavior within a specific time window in direct response to a signal from another ...
Adaptive integration of multiple cues for contingency detection
HBU'11: Proceedings of the Second international conference on Human Behavior UnterstandingCritical to natural human-robot interaction is the capability of robots to detect the contingent reactions by humans. In various interaction scenarios, a robot can recognize a human's intention by detecting the presence or absence of a human response to ...
Comments