Abstract
A potential barrier to an effective human-machine team is the mismatch between the learning dynamics of each teammate. Humans often master new cognitive-motor tasks quickly, but not instantaneously. In contrast, artificial systems often solve new tasks instantaneously (e.g., knowledge-based planning agents) or learn much more slowly than humans (e.g., reinforcement learning agents). In this work, we present our ongoing work on a robotic control architecture that blends planning and memory to produce more human-like learning dynamics. We empirically assess current implementations of four main components in this architecture: object manipulation, full-body motor control, robot vision, and imitation learning. Assessment is conducted using a simulated humanoid robot performing a maintenance task in a virtual tabletop setting. Finally, we discuss the prospects for using this learning architecture with human teammates in virtual and ultimately physical environments.
Supported by ONR award N00014-19-1-2044.
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
References
Blenkinsop, G.M., Pain, M.T., Hiley, M.J.: Balance control strategies during perturbed and unperturbed balance in standing and handstand. Royal Soc. Open Sci. 4(7), 161018 (2017)
Carpin, S., Liu, S., Falco, J., Wyk, K.V.: Multi-fingered robotic grasping: a primer (2016)
Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning. http://pybullet.org (2016–2021)
Hauge, T.C., Katz, G.E., Davis, G.P., Huang, D.W., Reggia, J.A., Gentili, R.J.: High-level motor planning assessment during performance of complex action sequences in humans and a humanoid robot. Int. J. Soc. Robot. 13(5), 981–998 (2021)
Hirai, K., Hirose, M., Haikawa, Y., Takenaka, T.: The development of honda humanoid robot. In: Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No. 98CH36146), vol. 2, pp. 1321–1326. IEEE (1998)
Hoffmann, J., Porteous, J., Sebastia, L.: Ordered landmarks in planning. J. Artif. Intell. Res. 22, 215–278, 161018 (2004)
Ji, S.Q., Huang, M.B., Huang, H.P.: Robot intelligent grasp of unknown objects based on multi-sensor information. Sensors 19(7) (2019). https://doi.org/10.3390/s19071595. https://www.mdpi.com/1424-8220/19/7/1595
Introduction to Humanoid Robotics. STAR, vol. 101. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-642-54536-8
Katz, G., Huang, D.W., Hauge, T., Gentili, R., Reggia, J.: A novel parsimonious cause-effect reasoning algorithm for robot imitation and plan recognition. IEEE Trans. Cogn. Dev. Syst. 10(2), 177–193, 161018 (2017)
Lapeyre, M., Rouanet, P., Oudeyer, P.Y.: The poppy humanoid robot: leg design for biped locomotion. In: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 349–356 (2013). https://doi.org/10.1109/IROS.2013.6696375
Lawler, E.L., Wood, D.E.: Branch-and-bound methods: A survey. Oper. Res. 14(4), 699–719 (1966)
Levenshtein, V.I., et al.: Binary codes capable of correcting deletions, insertions, and reversals. Soviet Phys. Doklady 10(8), 707–710, 161018 (1966)
Lin, Y., Sun, Y.: Robot grasp planning based on demonstrated grasp strategies. Int. J. Robot. Res. 34(1), 26–42 (2015). https://doi.org/10.1177/0278364914555544. https://doi.org/10.1177/0278364914555544
Marius, P., Balas, V., Perescu-Popescu, L., Mastorakis, N.: Multilayer perceptron and neural networks. WSEAS Trans. Circuits Syst. 8, June 2009
Saxena, A., Wong, L., Ng, A.: Learning grasp strategies with partial shape information. vol. 3, pp. 1491–1494 (2008)
Shaver, A., Shuggi, I., Katz, G., Davis, G., Reggia, J., Gentili, R.: Effects of practicing structured and unstructured complex motor sequences on performance and mental workload. In: Journal of Sport and Exercise Psychology, vol. 42, p. S56. Human Kinetics (2020)
Stephens, B.: Integral control of humanoid balance. In: 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4020–4027. IEEE (2007)
Tesauro, G., Galperin, G.: On-line policy improvement using Monte-Carlo search. Adv. Neural. Inf. Process. Syst. 9, 1068–1074, 161018 (1996)
Vukobratović, M., Borovac, B.: Zero-moment point-thirty five years of its life. Int. J. Humanoid Rob. 1(01), 157–173 (2004)
Winter, D.A.: Human balance and posture control during standing and walking. Gait Posture 3(4), 193–214, 161018 (1995)
Zaidi, L., Corrales, J.A., Bouzgarrou, B.C., Mezouar, Y., Sabourin, L.: Model-based strategy for grasping 3d deformable objects using a multi-fingered robotic hand. Robot. Autonomous Syst. 95, 196–206 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Akshay, Chen, X., He, B., Katz, G.E. (2022). Towards Human-Like Learning Dynamics in a Simulated Humanoid Robot for Improved Human-Machine Teaming. In: Schmorrow, D.D., Fidopiastis, C.M. (eds) Augmented Cognition. HCII 2022. Lecture Notes in Computer Science(), vol 13310. Springer, Cham. https://doi.org/10.1007/978-3-031-05457-0_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-05457-0_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05456-3
Online ISBN: 978-3-031-05457-0
eBook Packages: Computer ScienceComputer Science (R0)