PDF(2942 KB)
微小型机器鼠仿鼠行为学习与生成
Zihang Gao, Guanglu Jia, Hongzhao Xie, Qiang Huang, Toshio Fukuda, Qing Shi
工程（英文） ›› 2022, Vol. 17 ›› Issue (10) : 232-243.
PDF(2942 KB)
PDF(2942 KB)
微小型机器鼠仿鼠行为学习与生成
Learning Rat-Like Behavior for a Small-Scale Biomimetic Robot
现有的仿生机器鼠仅可以执行一些基本的仿鼠运动基元（MP），并通过这些基元的刚性组合来形成简单的行为。为了模拟具有高相似性的典型实验鼠行为，本文提出使用概率模型和运动特征对实验鼠的行为进行参数化。首先，对15 个10 min 的实验鼠运动视频片段的分析表明，一只实验鼠在野外通常有6 种典型的行为，且每种行为都包含8 个运动基元的不同组合。本文首先使用softmax 分类器来获得实验鼠的行为-运动分层概率模型。其次，使用静态和动态的运动参数对运动基元组合进行特征化。本文分别使用分层聚类和模糊C均值（FCM）聚类获得静态和动态运动参数的优势值。这些优势值通过二阶傅里叶级数对实验鼠的脊柱关节轨迹进行拟合，并且通过具有两个隐藏层的反向传播（BP）神经网络对关节轨迹进行泛化。最后，将分层概率模型和泛化的关节轨迹分别作为控制策略和指令映射到机器鼠。本文在机器鼠上实现了6 种典型的仿鼠行为，其结果与实验鼠的行为相比显示出高度相似性。
Existing biomimetic robots can perform some basic rat-like movement primitives (MPs) and simple behavior with stiff combinations of these MPs. To mimic typical rat behavior with high similarity, we propose parameterizing the behavior using a probabilistic model and movement characteristics. First, an analysis of fifteen 10min video sequences revealed that an actual rat has six typical behaviors in the open
field, and each kind of behavior contains different bio-inspired combinations of eight MPs. We used the softmax classifier to obtain the behavior-movement hierarchical probability model. Secondly, we specified the MPs using movement parameters that are static and dynamic. We obtained the predominant values of the static and dynamic movement parameters using hierarchical clustering and fuzzy C-means
clustering, respectively. These predominant parameters were used for fitting the rat spinal joint trajectory using a second-order Fourier series, and the joint trajectory was generalized using a back propagation neural network with two hidden layers. Finally, the hierarchical probability model and the generalized joint trajectory were mapped to the robot as control policy and commands, respectively. We implemented the six typical behaviors on the robot, and the results show high similarity when compared with the behaviors of actual rats.
Biomimetic / Bio-inspired robot / Neural network learning system / Behavior generation
| [1] |
Li L, Nagy M, Graving JM, Bak-Coleman J, Xie G, Couzin ID. Vortex phase matching as a strategy for schooling in robots and in fish. Nat Commun 2020;11:5408.
|
| [2] |
Floreano D, Ijspeert AJ, Schaal S. Robotics and neuroscience. Curr Biol 2014;24(18): 911–20.
|
| [3] |
Fernández-Juricic E, Gilak N, Mcdonald JC, Pithia P, Valcarcel A. A dynamic method to study the transmission of social foraging information in flocks using robots. Anim Behav 2006;71(4):901–11.
|
| [4] |
Son JH, Ahn HS. A robot learns how to entice an insect. IEEE Intell Syst 2015;30(4): 54–63.
|
| [5] |
Kopman V, Laut J, Polverino G, Porfiri M. Closed-loop control of zebrafish response using a bioinspired robotic-fish in a preference test. J R Soc Interface 2013;10(78):20120540.
|
| [6] |
Partan SR, Larco CP, Owens MJ. Wild tree squirrels respond with multisensory enhancement to conspecific robot alarm behaviour. Anim Behav 2009;77(5): 1127–35.
|
| [7] |
De Lellis P, Cadolini E, Croce A, Yang Y, di Bernardo M, Porfiri M. Model-based feedback control of live zebrafish behavior via interaction with a robotic replica. IEEE Trans Robot 2020;36(1):28–41.
|
| [8] |
Halloy J, Sempo G, Caprari G, Rivault C, Asadpour M, Taˆche F, et al. Social integration of robots into groups of cockroaches to control self-organized choices. Science 2007;318(5853):1155–8.
|
| [9] |
Gribovskiy A, Halloy J, Deneubourg JL, Mondada F. Designing a socially integrated mobile robot for ethological research. Robot Auton Syst 2018;103:42–55.
|
| [10] |
Ballerini M, Cabibbo N, Candelier R, Cavagna A, Cisbani E, Giardina I, et al. Interaction ruling animal collective behavior depends on topological rather than metric distance: evidence from a field study. Proc Natl Acad Sci USA 2008;105(4):1232–7.
|
| [11] |
Faria JJ, Dyer JRG, Clément RO, Couzin ID, Holt N, Ward AJW, et al. A novel method for investigating the collective behaviour of fish: introducing ‘‘Robofish”. Behav Ecol Sociobiol 2010;64(8):1211–8.
|
| [12] |
Marras S, Porfiri M. Fish and robots swimming together: attraction towards the robot demands biomimetic locomotion. J R Soc Interface 2012;9(73): 1856–68.
|
| [13] |
Klein BA, Stein J, Taylor RC. Robots in the service of animal behavior. Commun Integr Biol 2012;5(5):466–72.
|
| [14] |
Abdai J, Miklósi Á. Poking the future: When should we expect that animal– robot interaction becomes a routine method in the study of behavior? Anim Behav Cogn 2018;5(4):321–5.
|
| [15] |
Felix-Ortiz AC, Burgos-Robles A, Bhagat ND, Leppla CA, Tye KM. Bidirectional modulation of anxiety-related and social behaviors by amygdala projections to the medial prefrontal cortex. Neuroscience 2016;321:197–209.
|
| [16] |
Weiss O, Segev E, Eilam D. ‘‘Shall two walk together except they be agreed?” Spatial behavior in rat dyads. Anim Cogn 2015;18(1):39–51.
|
| [17] |
Shi Q, Gao J, Wang S, Quan X, Jia G, Huang Q, et al. Development of a smallsized quadruped robotic rat capable of multimodal motions. IEEE Trans Robot. In press.
|
| [18] |
Sullivan C, Loughlin R, Schank JC, Joshi SS. Genetic algorithms produce individual robotic rat pup behaviors that match Norway rat pup behaviors at multiple scales. Artif Life Robot 2015;20(2):93–102.
|
| [19] |
Ortiz RDA, Contreras CM, Gutiérrez-Garcia AG, González MFM. Social interaction test between a rat and a robot: a pilot study. Int J Adv Robot Syst 2016;13(4):62015.
|
| [20] |
Heath S, Ramirez-Brinez CA, Arnold J, Olsson O, Taufatofua J, Pounds P, et al. PiRat: an autonomous framework for studying social behaviour in rats and robots. In: Proceedings of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS); 2018 Oct 1–5; Madrid, Spain. IEEE; 2018. p. 7601–8.
|
| [21] |
Ahuja N, Lobellová V, Stuchlík A, Kelemen E. Navigation in a space with moving objects: rats can avoid specific locations defined with respect to a moving robot. Front Behav Neurosci 2020;14:576350.
|
| [22] |
Shi Q, Gao Z, Jia G, Li C, Huang Q, Ishii H, et al. Implementing rat-like motion for a small-sized biomimetic robot based on extraction of key movement joints. IEEE Trans Robot 2021;37(3):747–62.
|
| [23] |
Ding R, Yu J, Yang Q, Tan M, Zhang J. CPG-based behavior design and implementation for a biomimetic amphibious robot. In: Proceedings of 2011 IEEE International Conference on Robotics and Automation; 2011 May 9–13; Shanghai, China. IEEE; 2011. p. 209–14.
|
| [24] |
Ren Q, Xu J, Fan L, Niu X. A GIM-based biomimetic learning approach for motion generation of a multi-joint robotic fish. J Bionic Eng 2013;10(4):423–33.
|
| [25] |
Leos-Barajas V, Gangloff EJ, Adam T, Langrock R, van Beest FM, Nabe-Nielsen J, et al. Multi-scale modeling of animal movement and general behavior data using hidden Markov models with hierarchical structures. J Agric Biol Environ Stat 2017;22(3):232–48.
|
| [26] |
Cullen JA, Poli CL, Fletcher Jr RJ, Valle D. Identifying latent behavioral states in animal movement with M4, a nonparametric Bayesian method. Methods Ecol Evol 2022;13(2):432–46.
|
| [27] |
Fraley C, Raftery AE. How many clusters? Which clustering method? Answers via model-based cluster analysis. Comput J 1998;41(8):578–88.
|
| [28] |
Sarle WS, Kaufman L, Rousseeuw PJ. Finding groups in data: an introduction to cluster analysis. J Am Stat Assoc 1991;86(415):830.
|
| [29] |
Xu R, Wunsch D. Survey of clustering algorithms. IEEE Trans Neural Netw 2005;16(3):645–78.
|
| [30] |
Bezdek JC, Ehrlich R, Full W. FCM: the fuzzy C-means clustering algorithm. Comput Geosci 1984;10(2–3):191–203.
|
| [31] |
Prut L, Belzung C. The open field as a paradigm to measure the effects of drugs on anxiety-like behaviors: a review. Eur J Pharmacol 2003;463(1–3): 3–33.
|
| [32] |
Eilam D. Open-field behavior withstands drastic changes in arena size. Behav Brain Res 2003;142(1–2):53–62.
|
| [33] |
Barnett SA. The rat: a study in behavior. Canberra: Australian National University Press; 1976.
|
| [34] |
Whishaw IQ, Kolb B. The behaviour of the laboratory rat: a handbook with tests. New York: Oxford University Press; 2005.
|
| [35] |
Neveln ID, Tirumalai A, Sponberg S. Information-based centralization of locomotion in animals and robots. Nat Commun 2019;10:3655.
|
| [36] |
Karásek M, Muijres FT, De Wagter C, Remes BDW, De Croon GCHE. A tailless aerial robotic flapper reveals that flies use torque coupling in rapid banked turns. Science 2018;361(6407):1089–94.
|
| [37] |
de Miranda NA. Pearson’s correlation coefficient: a more realistic threshold for applications on autonomous robotics. Comput Technol Appl 2014;5: 69–72.
|
| [38] |
Park IW, Kim JY. Biomimetic walking trajectory generation of humanoid robot on an inclined surface using Fourier series. J Nanosci Nanotechnol 2014;14(10): 7533–9.
|
| [39] |
Inohira E, Uoi T, Yokoi H. Generalization capability of neural networks for generation of coordinated motion of a hybrid prosthesis with a healthy arm. Int J Innov Comput, Inf Control 2008;4(2):471–84.
|
| [40] |
Zhou D, Guo C, Liu R, Che C, Yang D, Zhang Q, et al. Hierarchical learning recurrent neural networks for 3D motion synthesis. Int J Mach Learn Cybern 2021;12(8):2255–67.
|
| [41] |
Wang G, Yang Y, Zhang H, Liu Z, Wang H. Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds. IEEE Trans Trans Cybern. In press.
|
| [42] |
Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Netw 1991;4(2):251–7.
|
| [43] |
Stathakis D. How many hidden layers and nodes? Int J Remote Sens 2009;30(8): 2133–47.
|
| [44] |
Shi Q, Li C, Li K, Huang Q, Ishii H, Takanishi A, et al. A modified robotic rat to study rat-like pitch and yaw movements. IEEE/ASME Trans Mechatron 2018;23(5):2448–58.
|
/
| 〈 |
|
〉 |
