Abstract
Skeleton designs are widely seen in the robotics industry and multimedia applications such as animated films and computer games. The design of skeletons is mental-labor intensive, especially axes directions of joints are difficult even for the most experienced designers to select. In the existing works, there are auto creation of skeletons from meshes, and skeleton axes optimizations from a predefined set of actions. In this work, we extend automatic construction of skeletons by proposing skeleton axes design from an objective task. A two-layered framework is proposed to optimize randomly initialized axes based on auto generated actions. First, the limit of skeleton scales that can be automatically designed is discussed. Second, a self-adaptive actions discretizer implemented by neural networks is proposed to reduce the optimization complexity. Third, actions and axes are scored by physics engine simulation, and optimizations on the score generate axes that have the best performance. Experiments include robotic designs and an animation application. Comparisons show that the proposed framework outperforms other mainstream optimizers both in speed and effectiveness.
Similar content being viewed by others
References
Andrei N (2017) Accelerated adaptive perry conjugate gradient algorithms based on the self-scaling memoryless BFGS update. J Comput Appl Math 325:149–164
Audet C, Hare W (2017) Nelder-mead. Springer, Cham, pp 75–91. https://doi.org/10.1007/978-3-319-68913-5_5
Baran I (2007) Automatic rigging and animation of 3d characters. ACM Trans Graph 26(3):72
Baskoro AS, Priyono MG (2016) Design of humanoid robot stable walking using inverse kinematics and zero moment point. In: 2016 International electronics symposium (IES). pp 335–339. https://doi.org/10.1109/ELECSYM.2016.7861027
Benassi R, Bect J, Vazquez E (2011) Robust gaussian process-based global optimization using a fully bayesian expected improvement criterion. In: Coello CAC (ed) Learning and intelligent optimization. Springer, Berlin, pp 176–190
Borga M (1993) Hierarchical reinforcement learning. In: Gielen S, Kappen B (eds) ICANN ’93. Springer, London, pp 513–513
Borosán P, Jin M, DeCarlo D, Gingold YI, Nealen A (2012) Rigmesh: automatic rigging for part-based shape modeling and deformation. ACM Trans Graph 31(6):198:1–198:9. https://doi.org/10.1145/2366145.2366217
Brochu E, Cora VM, de Freitas N (2010) A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. CoRR arXiv:1012.2599
Contal E, Buffoni D, Robicquet A, Vayatis N (2013) Parallel gaussian process optimization with upper confidence bound and pure exploration. In: Blockeel H, Kersting K, Nijssen S, Železný F (eds) Machine learning and knowledge discovery in databases. Springer, Berlin, pp 225–240
Francesca G, Brambilla M, Brutschy A, Trianni V, Birattari M (2014) Automode: a novel approach to the automatic design of control software for robot swarms. Swarm Intell 8(2):89–112
Freundlich C, Zhang Y, Zavlanos MM (2018) Distributed hierarchical control for state estimation with robotic sensor networks. IEEE Trans Control Netw Syst 5(4):2023–2035. https://doi.org/10.1109/TCNS.2017.2782481
Gao F, Han L (2012) Implementing the nelder-mead simplex algorithm with adaptive parameters. Comput Optim Appl 51(1):259–277. https://doi.org/10.1007/s10589-010-9329-3
Garrido-Merchán EC, Hernández-Lobato D (2018) Dealing with categorical and integer-valued variables in bayesian optimization with gaussian processes. arXiv:1805.03463
Gu F, Li K, Liu Y (2016) A hybrid evolutionary algorithm for solving function optimization problems. In: 2016 12th International conference on computational intelligence and security (CIS). pp 526–529. https://doi.org/10.1109/CIS.2016.0128
Hajari N, Cheng I, Basu A (2016) Robust human animation skeleton extraction using compatibility and correctness constraints. In: 2016 IEEE international symposium on multimedia (ISM). pp 271–274. https://doi.org/10.1109/ISM.2016.0060
Hess R (2010) Blender foundations: the essential guide to learning blender 2.6. Focal Press, Waltham
Hester T, Vecerík M, Pietquin O, Lanctot M, Schaul T, Piot B, Horgan D, Quan J, Sendonaris A, Osband I, Dulac-Arnold G, Agapiou J, Leibo JZ, Gruslys A (2018) Deep q-learning from demonstrations. In: Proceedings of the thirty-second AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2–7, 2018. pp 3223–3230. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16976
Jones E, Oliphant T, Peterson P et al (2001) SciPy: Open source scientific tools for Python. http://www.scipy.org/. Accessed 05 May 2019
Josuet L, Carlos B, Hsien-I L, Te-Sheng H, Chun-Sheng W (2016) An improved inverse kinematics solution of 6r-dof robot manipulators with euclidean wrist using dual quaternions. In: 2016 International automatic control conference (CACS). pp 77–82. https://doi.org/10.1109/CACS.2016.7973887
Kennedy J (2010) Particle swarm optimization. Springer, Boston, pp 760–766. https://doi.org/10.1007/978-0-387-30164-8_630
Knysh P, Korkolis Y (2016) Blackbox: A procedure for parallel optimization of expensive black-box functions. CoRR arXiv:1605.00998
Koubaa A (2016) Robot operating system (ROS). The complete reference (Volume 1). Springer. https://www.springer.com/gp/book/9783319260525
Kramer O (2016) Scikit-learn. Springer, Cham, pp 45–53. https://doi.org/10.1007/978-3-319-33383-0_5
Li D (2016) Towards real-time insect motion capture. In: Special interest group on computer graphics and interactive techniques conference, SIGGRAPH ’16, Anaheim, CA, USA, July 24–28, 2016, posters proceedings. pp 37:1–37:2. https://doi.org/10.1145/2945078.2945115
Li D, Wang W, Wang Q, Hao D (2016) Polishing robot structure optimization based on workspace analysis. In: 2016 Asia-Pacific conference on intelligent robot systems (ACIRS). pp 52–56. https://doi.org/10.1109/ACIRS.2016.7556187
Mousavi SS, Schukat M, Howley E (2018) Deep reinforcement learning: an overview. In: Bi Y, Kapoor S, Bhatia R (eds) Proceedings of SAI intelligent systems conference (IntelliSys) 2016. Springer, Cham, pp 426–440
Muñoz MA, Sun Y, Kirley M, Halgamuge SK (2015) Algorithm selection for black-box continuous optimization problems: a survey on methods and challenges. Inf Sci 317:224–245. https://doi.org/10.1016/j.ins.2015.05.010
Najafabadi MM, Khoshgoftaar TM, Villanustre F, Holt J (2017) Large-scale distributed l-bfgs. J Big Data 4(1):22
Powell MJD (1994) A direct search optimization method that models the objective and constraint functions by linear interpolation. Springer, Dordrecht, pp 51–67. https://doi.org/10.1007/978-94-015-8330-5_4
pybullet (2017) Bullet real-time physics simulation. https://pybullet.org. Accessed 5 May 2019
Schuitema E, Wisse M, Ramakers T, Jonker P (2010) The design of leo: a 2d bipedal walking robot for online autonomous reinforcement learning. In: 2010 IEEE/RSJ international conference on intelligent robots and systems. pp 3238–3243. https://doi.org/10.1109/IROS.2010.5650765
Sifakis E, Neverov I, Fedkiw R (2005) Automatic determination of facial muscle activations from sparse motion capture marker data. ACM Trans Graph 24(3):417–425. https://doi.org/10.1145/1073204.1073208
Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms. In: Proceedings of the 31st international conference on international conference on machine learning—volume 32, ICML’14. pp I–387–I–395. JMLR.org. http://dl.acm.org/citation.cfm?id=3044805.3044850
Snoek J, Larochelle H, Adams RP (2012) Practical bayesian optimization of machine learning algorithms. In: Proceedings of the 25th international conference on neural information processing systems—volume 2, NIPS’12. pp 2951–2959. Curran Associates Inc., USA. http://dl.acm.org/citation.cfm?id=2999325.2999464
Terada Y, Murata S (2004) Automatic assembly system for a large-scale modular structure—hardware design of module and assembler robot. In: 2004 IEEE/RSJ international conference on intelligent robots and systems (IROS) (IEEE Cat. No.04CH37566), vol 3. pp 2349–2355 https://doi.org/10.1109/IROS.2004.1389760
tisimst (2013) pyswarm. https://pythonhosted.org/pyswarm/. Accessed 28 Aug 2019
Wang D, Wang C, Xiao J, Xiao Z, Chen W, Havyarimana V (2019) Bayesian optimization of support vector machine for regression prediction of short-term traffic flow. Intell Data Anal 23(2):481–497. https://doi.org/10.3233/IDA-183832
Wild SM, Shoemaker CA (2013) Global convergence of radial basis function trust-region algorithms for derivative-free optimization. SIAM Rev 55(2):349–371. https://doi.org/10.1137/120902434
Yue C, Qu B, Liang J (2018) A multiobjective particle swarm optimizer using ring topology for solving multimodal multiobjective problems. IEEE Trans Evol Comput 22(5):805–817. https://doi.org/10.1109/TEVC.2017.2754271
Zarrin A, Azizi S, Aliasghary M (2019) A novel inverse kinematics scheme for the design and fabrication of a five degree of freedom arm robot. Int J Dyn Control. https://doi.org/10.1007/s40435-019-00558-1
Zhang R, Zhong Y,Wei D, Dan OP (2017) Design and fabrication of an articulated four axes microrobot arm. In: Brian MC, Douglas K, Eric SM (eds) Society of photo-optical instrumentation engineers, vol 10216. SPIE. https://doi.org/10.1117/12.22628146
Funding
This study was funded by Science Foundation of China (Grant Number 61602421).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Authors declare no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Communicated by V. Loia.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xiang, Z., Xiang, C., Li, T. et al. A self-adapting hierarchical actions and structures joint optimization framework for automatic design of robotic and animation skeletons. Soft Comput 25, 263–276 (2021). https://doi.org/10.1007/s00500-020-05139-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-020-05139-5