Generalization of movements in quadruped robot locomotion by learning specialized motion data
Tóm tắt
Machines that are sensitive to environmental fluctuations, such as autonomous and pet robots, are currently in demand, rendering the ability to control huge and complex systems crucial. However, controlling such a system in its entirety using only one control device is difficult; for this purpose, a system must be both diverse and flexible. Herein, we derive and analyze the feature values of robot sensor and actuator data, thereby investigating the role that each feature value plays in robot locomotion. We conduct experiments using a developed quadruped robot from which we acquire multi-point motion information as the movement data; we extract the features of these movement data using an autoencoder. Next, we decompose the movement data into three features and extract various gait patterns. Despite learning only the “walking” movement, the movement patterns of trotting and bounding are also extracted herein, which suggests that movement data obtained via hardware contain various gait patterns. Although the present robot cannot locomote with these movements, this research suggests the possibility of generating unlearned movements.
Tài liệu tham khảo
Eadweard Muybridge (Chapman and Hall, London, 1899, 1957) Animals in Motion. Dover Pub
Hoyt Donald F, Richard Taylor C (1981) Gait and the energetics of locomotion in horses. Nature 292(16):239–240
Hildebrand Milton (1965) Symmetrical gaits of horses. Science 150:701–708
Thomas Graham Brown and Charles Scott Sherrington (1911) The intrinsic factor in the act of progression in the mammal. Proc R Soc London Ser B84:308–319
Grillner S, Zangger P (1979) On the central generation of locomotion in the low spinal cat. Exp Brain Res 34:241–261
Grillner S (1975) Locomotion in vertebrates: central mechanisms and reflex interaction. Physiol. Review 55:367–371
Shik ML, Orlovsky GN (1976) Neurophysiology of locomotor automatism. Physiol Rev 56:465–501
Philippson M (1905) L’autonomie et la centralisation dans le système nerveux des animaux Bruxelles, Falk 7: l–208
Afelt Z, Kasicki S (1975) Limb coordinations during locomotion in cats and dogs. Acta Neurobiol. Exp. 35:369–376
Owaki Dai, Ishiguro Akio (2017) A quadruped robot exhibiting spontaneous gait transitions from walking to trotting to galloping. Sci Rep 7(1):277
Fukuoka Y et al (2013) Analysis of the gait generation principle by a simulated quadruped model with a CPG incorporating vestibular modulation. Biol Cybern 107:695–710
Fukuoka Yasuhiro, Habu Yasushi, Fukui Takahiro (2015) A simple rule for quadrupedal gait generation determined by leg loading feedback: a modeling study. Sci Rep 5:8169
Righetti L, Ijspeert AJ (2008) Pattern generators with sensory feedback for the control of quadruped locomotion. In: IEEE international conference on robotics and automation. pp 819–824
Auke Jan Ijspeert (2008) Central pattern generators for locomotion control in animals and robots. Preprint of Neural Netw 21(4):642–653
Kimura Hiroshi (1999) Realization of dynamic walking and running of the quadruped using neural oscillator. Autonomous Robots 7(3):247–258
LaValle SM (2006) Planning algorithms
van der Weele JP, Banning EJ (2001) Mode interaction in horses, tea, and other nonlinear oscillators: the universal role of symmetry. Am J Phys 69:953
Funato T, Aoi S, Oshima H, Tsuchiya K (2010) Variant and invariant patterns embedded in human locomotion through whole body kinematic coordination. Exp Brain Res 205:497–511
Mussa-Ivaldi FA, Giszter SF, Bizzi E (1994) Linear combinations of primitives in vertebrate motor control. Proc Natl Acad Sci USA 91:7534–7538
Grillner S (1985) Neurobiological bases of rhythmic motor acts in vertebrates. Science 228:143–149
Ivanenko YP, Poppele RE, Lacquaniti F (2004) Five basic muscle activation patterns account for muscle activity during human locomotion. J Physiol 556:267
Biancardi Carlo M, Minetti Alberto E (2012) Biomechanical determinants of transverse and rotary gallop in cursorial mammals. J Exp Biol 215:4144–4156
Biewener Andrew A (1990) Biomechanics of mammalian terrestrial locomotion. Science 250(4984):1097–1103
Cohen Avis H, Gans Carl (1975) Muscle activity in rat locomotion: movement analysis and electromyography of the flexors and extensors of the elbow. J Morphol 146:177–196
Wickler SJ, Hoyt DF, Cogger EA, Myers G (2003) The energetics of the trot-gallop transition. J Exp Biol 206:1557–1564
Schöner G, Jiang WY, Kelso JA (1990) A synergetic theory of quadrupedal gaits and gait transitions. J Theor Biol 142:359–391
Golubitsky M, Stewart I, Buono PL, Collins JJ (1999) Symmetry in locomotor central pattern generators and animal gaits. Nature 401:693–695
Bassler U (1986) On the definition of central pattern generator and its sensory control. Biol Cybern 54:65–69
Aoi Shinya, Manoonpong Poramate, Ambe Yuichi, Matsuno Fumitoshi (2017) Adaptive control strategies for interlimb coordination in legged robots: a review. Front Neurorobot 11:39
Kuo Arthur D (2002) The relative roles of feedforward and feedback in the control of rhythmic movements. Mot Control 6:129–145
Willems JC, Polderman JW (1998) Introduction to mathematical systems theory: a behavioral approach. Springer, Berlin
Willems JC (1991) Paradigms and puzzles in the theory of dynamical systems. IEEE Trans Automat Control 36:259–294
Willems JC (1997) On interconnections, control and feedback. IEEE Trans Automat Control 42:326–339
Dominici N, Ivanenko YP, Cappellini G, d’Avella A, Mondì V, Cicchese M, Fabiano A, Silei T, Di Paolo A, Giannini C, Poppele RE, Lacquaniti F (2011) Locomotor primitives in newborn babies and their development. Science 334:997
d’Avella Andrea, Saltiel Philippe, Bizzi Emilio (2003) Combinations of muscle synergies in the construction of a natural motor behavior. Nat Neurosci 6:300–308
d’Avella A, Tresch MC (2001) Modularity in the motor system: decomposition of muscle patterns as combinations of time-varying synergies. Adv Neural Inf Process Syst 14:141–148
Ijspeert A, Nakanishi J, Hoffmann H, Pastor P, Schaal S (2013) Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput 25(2):328–373
Holden D, Saito J, Komura T, Joyce T (2015) Learning motion manifolds with convolutional autoencoders. SIGGRAPH Asia Technical Briefs Article No. 18
Troje Nikolaus F (2002) Decomposing biological motion: a framework for analysis and synthesis of human gait patterns. J Vision 2:371–387
Chen N, Bayer J, Urban S, van der Smagt P (2015) Efficient movement representation by embedding dynamic movement primitives in deep autoencoders. In: International conference on humanoid robots
Chen N (2017) Efficient movement representation and prediction with machine learning. Doctoral dissertation, Technische Universität München
Y Motegi, Y Hijioka, M Murakami (2018) Human motion generative model using variational autoencoder. Int J Model Optim 8(1)
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
Moore BC (1981) Principal component analysis in linear systems: controllability, observability and model reduction. IEEE Trans Autom Control 26(1):17–32
Hoerl E, Kennard RW (1970) Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12(1):55–67
Kurita Y, Matsumura Y, Kanda S, Kinugasa H (2008) Gait patterns of quadrupeds and natural vibration modes. J Syst Design Dyn 2(6):1316–1326
Tero A, Akiyama M, Owaki D, Kano T, Ishiguro A, Kobayashi R (2013) Interlimb neural connection is not required for gait transition in quadruped locomotion. arXiv preprint arXiv:1310.7568
Kano T, Owaki D, Fukuhara A, Kobayashi R, Ishiguro A (2015) New hypothesis for the mechanism of quadruped gait transition. In: The 1st international symposium on swarm behavior and bio-inspired robotics, pp 275–278