Abstract
In this paper, we propose a framework for generating coordinated periodic movements of robotic systems with multiple external inputs. We developed an adaptive pattern generator model that is composed of a two-factor observation model with a style parameter and phase dynamics with a phase variable. The style parameter controls the spatial patterns of the generated trajectories, and the phase variable manages its temporal profiles. By exploiting the style–phase separation in the pattern generation, we can independently design adaptation schemes for the spatial and temporal profiles of the pattern generator to multiple external inputs. To validate the effectiveness of our proposed method, we applied it to a user–exoskeleton model to achieve user-adaptive walking assistance for which the exoskeleton robot’s movements need to be coordinated with the user walking patterns and environment. As a result, the exoskeleton robot successfully performed stable biped walking behaviors for walking assistance even when the style of the observed walking pattern and the period were suddenly changed.
Similar content being viewed by others
References
André J, Teixeira C, Santos C, Costa L (2015) Adapting biped locomotion to sloped environments. J Intell Robot Syst 1–16. doi:10.1007/s10846-015-0196-0
Brand M, Hertzmann A (2000) Style machines. In: Proceedings of the 2000 SIGGRAPH, pp 183–192
Degallier S, Righetti L, Gay S, Ijspeert A (2011) Toward simple control for complex, autonomous robotic applications: combining discrete and rhythmic motor primitives. Auton Robot 31(2–3):155–181
Endo G, Morimoto J, Nakanishi J, Cheng G (2004) An empirical exploration of a neural oscillator for biped locomotion control. In: Proceedings of the 2004 IEEE international conference on robotics and automation, pp 3036–3042
Endo G, Morimoto J, Matsubara T, Nakanishi J, Cheng G (2008) Learning CPG-based biped locomotion with a policy gradient method: apply to a humanoid robot. Int J Robot Res 27(2):213–228
Fukuoka Y, Kimura H, Cohen A (2003) Adaptive dynamic walking of a quadruped robot on irregular terrain based on biological concepts. Int J Robot Res 22(3–4):187–202
Gams A, Ijspeert AJ, Schaal S, Lenarcic J (2009) On-line learning and modulation of periodic movements with nonlinear dynamical systems. Auton Robot 27(1):3–23
Hase K, Yamazaki N (1998) Computer simulation of the ontogeny of biped walking. Anthropol Sci 106(4):327–347
Hyon S, Morimoto J, Matsubara T, Noda T, Kawato M (2011) XoR: hybrid drive exoskeleton robot that can balance. In: Proceedings of the IEEE/RSJ international conference on intelligent robots and systems, pp 2715–2722
Kanda T, Ishiguro H, Imai M, Ono T (2003) Body movement analysis of human–robot interaction. In: Proceedings of the international joint conference on artificial intelligence, pp 177–182
Kotosaka S, Schaal S (2000) Synchronized robot drumming by neural oscillator. In: Proceedings of the international symposium on adaptive motion of animals and machines, pp 1–8
Li C, Lowe R, Ziemke T (2014) A novel approach to locomotion learning: actor-critic architecture using central pattern generators and dynamic motor primitives. Front Neurorobot 8(23):1–17
Matos V, Santos CP (2014) Towards goal-directed biped locomotion: combining CPGs and motion primitives. Robot Auton Syst 62(12):1669–1690
Matsubara T, Morimoto J (2013) Bilinear modeling of EMG signals to extract user-independent features for multiuser myoelectric interface. IEEE Trans Biomed Eng 60(8):2205–2213
Matsubara T, Hyon S, Morimoto J (2011) Learning parametric dynamic movement primitives from multiple demonstrations. Neural Netw 24(5):493–500
Matsubara T, Hyon S, Morimoto J (2012) Real-time stylistic predictions for whole-hody human motions. Neural Netw 25(1):191–199
Matsubara T, Morimoto J, Nakanishi J, Sato M, Doya K (2006) Learning CPG-based biped locomotion with a policy gradient method. Robot Auton Syst 54:911–920
Matsuoka K (1985) Sustained oscillations generated by mutually inhibiting neurons with adaptation. Biol Cybern 52:367–376
Michalowski MP, Kozima H, Abanovi S (2007) A dancing robot for rhythmic social interaction. In: Proceedings of the ACM/IEEE international conference on human–robot interaction, pp 1–8
Morimoto J, Noda T, Hyon S (2012) Extraction of latent kinematic relationships between human users and assistive robots. In: Robotics and automation (ICRA), 2012 IEEE international conference on, pp 3909–3915
Morimoto J, Endo G, Nakanishi J, Cheng G (2008) A biologically inspired biped locomotion strategy for humanoid robots: modulation of sinusoidal patterns by a coupled oscillator model. IEEE Trans Robot 24(1):185–191
Nakamura Y, Mori T, Sato M, Ishii S (2007) Reinforcement learning for a biped robot based on a CPG-actor-critic method. Neural Netw 20(6):723–735
Nakanishi J, Morimoto J, Endo G, Cheng G, Schaal S, Kawato M (2004) Learning from demonstration and adaptation of biped locomotion. Robot Auton Syst 47(2–3):79–91
Nassour J, Hénaff P, Benouezdou F, Cheng G (2014) Multi-layered multi-pattern CPG for adaptive locomotion of humanoid robots. Biol Cybern 108(3):291–303
Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning. MIT Press, Cambridge
Righetti L, Ijspeert AJ (2006) Programmable central pattern generators: an application to biped locomotion control. In: Proceedings of the IEEE international conference on robotics and automation, pp 1585–1600
Righetti L, Buchli J, Ijspeert AJ (2006) Dynamic hebbian learning in adaptive frequency oscillators. Phys D 216(2):269–281
Ronsse R, Vitiello N, Lenzi T, van den Kieboom J, Carrozza M, Ijspeert A (2010) Adaptive oscillators with human-in-the-loop: proof of concept for assistance and rehabilitation. In: Proceedings of the IEEE international conference on biomedical robotics and biomechatronics, pp 668–674
Ronsse R, Lenzi T, Vitiello N, Koopman B, vanAsseldonk E, Rossi SD, van den Kieboom J, van der Kooij K, Carrozza M, Ijspeert A (2011) Oscillator-based walking assistance: a model-free approach. In: Proceedings of the IEEE international conference on rehabilitation robotics 2011, pp 1–6
Silva P, Santos CP, Matos V, Costa L (2014) Automatic generation of biped locomotion controllers using genetic programming. Robot Auton Syst 62(10):1531–1548
Strogtz SH (1994) Nonlinear dynamics and chaos. Westview Press, Cambridge
Suzuki K, Mito G, Kawamoto H, Hasegawa Y, Sankai Y (2007) Intention-based walking support for paraplegia patient with robot SuitHAL. Adv Robot 21(12):1441–1469
Taga G, Yamaguchi Y, Shimizu H (1991) Self-organized control of bipedal locomotion by neural oscillators in unpredictable environment. Biol Cybern 65:147–159
Taylor GW, Hinton GE (2009) Factored conditional restricted Bolzmann machines for modeling motion style. In: Proceedings of the 26th annual international conference on machine learning, 2009, pp 1025–1032
Tenenbaum JB, Freeman WT (2000) Separating style and content with bilinear models. Neural Comput 12(6):1247–1283
Tsuchiya K, Aoi S, Tsujita K (2003) Locomotion control of a biped locomotion robot using nonlinear oscillator. In: Proceedings of the 2003 IEEE/RSJ international conference on intelligent robots and systems, pp 1745–1750
Wang JM, Fleet DJ, Hertzmann A (2007) Multifactor Gaussian process models for style-content separation. In: Proceedings of the 24th annual international conference on machine learning, pp 975–982
Zhang X, Hashimoto M (2009) SBC for Motion Assist Using Neural Oscillator. In: Proceedings of the IEEE international conference on robotics and automation 2009, pp 659–664
Acknowledgments
This study is the result of Development of BMI Technologies for Clinical Application carried out under SRPBS, MEXT; by MIC-SCOPE; International Cooperative Program, JST and by JSPS and MIZS: Japan-Slovenia research Cooperative Program; by MEXT KAKENHI 23120004; and by JSPS KAKENHI Grant Number 25540085; by ImPACT Program of Council for Science, Technology and Innovation (Cabinet Office, Government of Japan); by the project commissioned by the New Energy and Industrial Technology Development Organization (NEDO).
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1: Learning procedure of pattern generator model
Data alignment by phase information Focusing on the periodicity of the target motions, we utilize autocorrelative and cross-correlative coefficients for the alignment process. First, we maximize the autocorrelative coefficient for identifying the period T of each sequence as: \(T^s \leftarrow \arg \max _j A^{s}(j)\), where \(A^{s}(j) =\sum _n^N { \mathbf{y} ^s_n}^T \mathbf{y} ^s_{n+j}\) is the autocorrelative coefficient with the self-index shift j in phase with a style indexed by s. Next, we maximize the cross-correlative coefficient to find the optimal cross-index shift h in phase as: \(h^s \leftarrow \arg \max _j C^{s}(j)\), where \(C^{s}(j) = \sum _n^N { \mathbf{y} ^{b}_n}^T \mathbf{y} ^s_{j + \mathrm{rd}\left( \frac{n T^s}{T^b}\right) }\) is the cross-correlative coefficient and index b is the style index corresponding to the sequence that has the shortest period. \(T^b\) is the period of the shortest period indexed by b. The function \(\mathrm{rd(\cdot )}\) is a round-off function. The above procedures yield an aligned data matrix:
where \( \mathbf{Y} ^\mathrm{all}_a = [ \mathbf{Y} _a^1 \cdots \mathbf{Y} _a^S]^T \in \mathbb {R}^{DS \times C}\), \( \mathbf{Y} _a^s \in \mathbb {R}^{C \times D}\), and C is the number of aligned data samples. Note that each row of the matrix \( \mathbf{Y} ^\mathrm{all}_a\) is the observations corresponding to the same value of the phase \(\phi \). Each column indicates a corresponding motion sequence indexed by s.
Extraction of observation bases Since the aligned data matrix \( \mathbf{Y} ^\mathrm{all}_a\) is a rectangular matrix, singular value decomposition (SVD)-based matrix factorization can be applied to extract the observation bases. By applying the factorization, we can form a style–content factorial model [referred to as the asymmetric bilinear model in Tenenbaum and Freeman (2000)].
Let \({ \mathbf{Y} ^\mathrm{all}_a}^\mathrm{VT}\) be an \(S \times DC\) matrix stacked from \(DS \times C\) Matrix \( \mathbf{Y} ^\mathrm{all}_a\). Then, SVD for this matrix leads to the following factorial representation as
We define the style parameter matrix \( \mathbf{W} = [ \mathbf{w} ^1 \cdots \mathbf{w} ^S]^T \in \mathbb {R}^{S \times J}\) to be the first \(J (\le S)\) rows of \( \mathbf{U} \), and the content parameter matrix \(\tilde{ \mathbf{Y} } = ( {[\bar{ \mathbf{Y} }^1 \cdots {\bar{ \mathbf{Y} }^J}]}^T )^\mathrm{VT} \in \mathbb {R}^{J \times DC}\) to be the first J columns of \( \mathbf{S} \mathbf{V} ^T\). As a result, we can obtain an approximated form as \( \mathbf{Y} ^s_a \approx \sum _{j=1}^{J} w_j^s \bar{ \mathbf{Y} }^j\). The obtained matrix \(\bar{ \mathbf{Y} }^j \in \mathbb {R}^{C \times D}\) is named the jth observation basis, and the vector \( \mathbf{w} ^s \in \mathbb {R}^J\) is the sth style parameter.
Learning a two-factor observation model with bases With the extracted bases \(\bar{ \mathbf{Y} }^j\) for all j, we can learn the observation model. Since each point of a basis corresponds to a value of phase, we learn a mapping between \(\bar{ \mathbf{y} }^j\) and \( \mathbf{z} \) using all data of each basis. Here we utilize a Gaussian process regression (Rasmussen and Williams 2006) because it allows us to derive an analytically tractable predictive distribution and to learn hyper-parameters by maximization of the marginalized likelihood.
Each basis \(\bar{ \mathbf{Y} }^j\) is independently modeled as a Gaussian process as \(p(\bar{ \mathbf{Y} }^j| \mathbf{Z} ,\varvec{\beta }^j) \propto \exp \left( -\frac{1}{2} \mathrm{Tr} \left( ( \mathbf{K} _y^j)^{-1} \bar{ \mathbf{Y} }^j (\bar{ \mathbf{Y} }^j)^T \right) \right) \) where \( \mathbf{Z} \) is the phase-aligned matrix corresponding to \(\bar{ \mathbf{Y} }^j\) and \( \mathbf{z} = \mathbf{h} (\phi ) = [\cos (\phi );\sin (\phi )]^T\) is a transformed variable of the phase \(\phi \) to approximately measure the geodesic distance between points on \(\mathbb {S}\) as the Euclidean distance in \(\mathbb {R}^2\) and \( \mathbf{K} ^j_y \in \mathbb {R}^{C \times C}\) is the gram matrix in which (p, q) entry is \(k^j_y( \mathbf{z} _p, \mathbf{z} _q)=\beta ^j_1 \exp \left( -\frac{\beta ^j_2}{2}|| \mathbf{z} _p- \mathbf{z} _q||^2\right) + \delta _{ \mathbf{z} _p, \mathbf{z} _q}/\beta ^j_3\), and the hyper-parameter is represented as \(\varvec{\beta }^j=\{\beta ^j_1, \beta ^j_2, \beta ^j_3\}\). With the above settings, the predictive distribution of the jth basis \(\bar{ \mathbf{y} }^{j*}\) given a novel input \( \mathbf{z} ^*\) can be easily derived as \(p(\bar{ \mathbf{y} }^{j*}| \mathbf{z} ^*,\bar{ \mathbf{Y} }^j, \mathbf{Z} ) = \mathcal {N}(\bar{\mu }^j( \mathbf{z} ^*),\bar{\varSigma }^j( \mathbf{z} ^*))\) where \(\bar{\mu }^j( \mathbf{z} ^*) = (\bar{ \mathbf{Y} }^j)^T ( \mathbf{K} ^j_y)^{-1} \mathbf{k} ^j_y( \mathbf{z} ^*)\), \(\bar{\varSigma }^j( \mathbf{z} ^*) = \left( k^j_y( \mathbf{z} ^*, \mathbf{z} ^*) - \mathbf{k} ^j_y( \mathbf{z} ^*)^T ( \mathbf{K} ^j_y)^{-1} \mathbf{k} ^j_y( \mathbf{z} ^*) \right) \mathbf{I} \) and \( \mathbf{k} ^j_y( \mathbf{z} ^*) = [k^j_y( \mathbf{z} ^*, \mathbf{z} _1) \cdots k^j_y( \mathbf{z} ^*, \mathbf{z} _C)]^T\) (Rasmussen and Williams 2006).
As the result, we extract the mean of the prediction distribution as the basis \( \mathbf{f} _j(\cdot ) = \bar{\mu }^j(\cdot )\) and obtain the observation model of the adaptive pattern generator in Eq. (2) as
Appendix 2: Two-dimensional coupled oscillator model
Here we consider the behavior of two-dimensional coupled-phase oscillator model of \(\{\phi _1, \phi _2\}\) as:
where \(\omega _1 > 0\) and \(\omega _2 > 0\) are natural frequencies of each oscillator, and \(K_1\) and \(K_2\) are positive coupling gains. The dynamics of the phase difference \(\varPhi = \phi _1 - \phi _2\) is given as \(\dot{\varPhi } = \dot{\phi }_1 - \dot{\phi }_2 = (\omega _1 - \omega _2) - (K_1 + K_2)\sin (\varPhi )\).
Because of its simple structure, we can easily find two fixed points if \(|\omega _1 - \omega _2|< K_1 + K_2\). There is no fixed point if \(|\omega _1 - \omega _2|> K_1 + K_2\). A saddle-node bifurcation occurs when \(|\omega _1 - \omega _2|= K_1 + K_2\). If \(|\omega _1 - \omega _2|< K_1 + K_2\), the coupled oscillator runs with the phase difference \(\varPhi ^* = |\phi _2 - \phi _1| = \sin ^{-1} \left( \left( \omega _2 - \omega _1 \right) /\left( K_1 + K_2\right) \right) \) and with the compromise frequency \(\omega ^* = (K_2 \omega _1 + K_1 \omega _2)/(K_2 + K_1)\) (Strogtz 1994).
Appendix 3: Style–phase estimation procedures
E-step The goal of this step is to compute the estimate for the current state from the estimate for the previous time step and current observation. To this end, we first compute the predictive distribution:
Then, by using the current observation \( \mathbf{y} _t\), the estimate is updated for the current time step:
where
M-step The goal of this step is to update the new style parameter \(\hat{ \mathbf{w} }\) with the estimate of the state given in E-step and the observation at the current time step. To this end, we define the time-forgetting weighted mean as follows:
where \(\lambda (0 \le \lambda \le 1)\) is a time-dependent forgetting factor which is introduced for forgetting the effect of the past observations. By using the mean, we can update the style parameter recursively:
where
Rights and permissions
About this article
Cite this article
Matsubara, T., Uchikata, A. & Morimoto, J. Spatiotemporal synchronization of biped walking patterns with multiple external inputs by style–phase adaptation. Biol Cybern 109, 597–610 (2015). https://doi.org/10.1007/s00422-015-0663-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-015-0663-5