TY  - JOUR
T1  - Control Through Contact using Mixture of Deep Neural-Net Experts
AU  - Satici, Aykut
PY  - 2025
DA  - June
Y2  - 2025
DO  - 10.17694/bajece.1515854
JF  - Balkan Journal of Electrical and Computer Engineering
PB  - MUSA YILMAZ
WT  - DergiPark
SN  - 2147-284X
SP  - 164
EP  - 173
VL  - 13
IS  - 2
LA  - en
AB  - We provide a data-driven control design frameworkfor hybrid systems, with a special emphasis on contact-richrobotic systems. These systems exhibit continuous state flowsand discrete state transitions, which are governed by distinctequations of motion. Hence, it may be impossible to design asingle policy that can control the system in all modes. Typically,hybrid systems are controlled by multi-modal policies, eachmanually triggered based on observed states. However, as thenumber of potential contacts increase, the number of policies cangrow exponentially and the control-switching scheme becomestoo complicated to parameterize. To address this issue, wedesign contact-aware data-driven controllers given by deepnetmixture of experts (MoE). This architecture automaticallylearns switching-control scheme that can achieve the desiredoverall performance of the system, and a gating network, whichdetermines the region of validity of each expert, based on theobserved states.
KW  - robotics
KW  - nonlinear control
KW  - machine learning
CR  - [1] M. Cutkosky, “On grasp choice, grasp models, and the design of
hands for manufacturing tasks,” IEEE Transactions on Robotics and
Automation, vol. 5, no. 3, pp. 269–279, 1989.
CR  - [2] X. Cheng, E. Huang, Y. Hou, and M. T. Mason, “Contact mode guided
motion planning for quasidynamic dexterous manipulation in 3d,” in
2022 International Conference on Robotics and Automation (ICRA),
pp. 2730–2736, IEEE, 2022.
CR  - [3] F. Ruggiero, V. Lippiello, and B. Siciliano, “Nonprehensile dynamic
manipulation: A survey,” IEEE Robotics and Automation Letters, vol. 3,
no. 3, pp. 1711–1718, 2018.
CR  - [4] F. Ruggiero, A. Petit, D. Serra, A. C. Satici, J. Cacace, A. Donaire,
F. Ficuciello, L. R. Buonocore, G. A. Fontanelli, V. Lippiello, et al.,
“Nonprehensile manipulation of deformable objects: Achievements and
perspectives from the robotic dynamic manipulation project,” IEEE
Robotics & Automation Magazine, vol. 25, no. 3, pp. 83–92, 2018.
CR  - [5] K. M. Lynch and T. D. Murphey, “Control of nonprehensile manipulation,”
in Control problems in robotics, pp. 39–57, Springer, 2003.
CR  - [6] K. M. Lynch and M. T. Mason, “Dynamic nonprehensile manipulation:
Controllability, planning, and experiments,” The International Journal
of Robotics Research, vol. 18, no. 1, pp. 64–92, 1999.
CR  - [7] M. Erdmann, “An exploration of nonprehensile two-palm manipulation,”
The International Journal of Robotics Research, vol. 17, no. 5, pp. 485–
503, 1998.
CR  - [8] M. Yashima, Y. Shiina, and H. Yamaguchi, “Randomized manipulation
planning for a multi-fingered hand by switching contact modes,” in 2003
IEEE International Conference on Robotics and Automation (Cat. No.
03CH37422), vol. 2, pp. 2689–2694, IEEE, 2003.
CR  - [9] J. Z. Woodruff and K. M. Lynch, “Planning and control for dynamic,
nonprehensile, and hybrid manipulation tasks,” in 2017 IEEE International
Conference on Robotics and Automation (ICRA), pp. 4066–4073,
IEEE, 2017.
CR  - [10] K. Lowrey, S. Kolev, J. Dao, A. Rajeswaran, and E. Todorov, “Reinforcement
learning for non-prehensile manipulation: Transfer from
simulation to physical system,” in 2018 IEEE International Conference
on Simulation, Modeling, and Programming for Autonomous Robots
(SIMPAR), pp. 35–42, IEEE, 2018.
CR  - [11] X. Zhang, M. Chang, P. Kumar, and S. Gupta, “Diffusion meets
dagger: Supercharging eye-in-hand imitation learning,” arXiv preprint
arXiv:2402.17768, 2024.
CR  - [12] C. M. Bishop, “Pattern recognition,” Machine learning, vol. 128, no. 9,
2006.
CR  - [13] T. H¨ark¨onen, S. Wade, K. Law, and L. Roininen, “Mixtures of gaussian
process experts with smc2,” arXiv preprint arXiv:2208.12830, 2022.
CR  - [14] M. I. Jordan and R. A. Jacobs, “Hierarchical mixtures of experts and the
em algorithm,” Neural computation, vol. 6, no. 2, pp. 181–214, 1994.
CR  - [15] Z. Chen, Y. Deng, Y. Wu, Q. Gu, and Y. Li, “Towards understanding
mixture of experts in deep learning,” arXiv preprint arXiv:2208.02813,
2022.
CR  - [16] M. M. Zhang and S. A. Williamson, “Embarrassingly parallel inference
for gaussian processes,” Journal of Machine Learning Research, 2019.
CR  - [17] L. V. Jospin, W. Buntine, F. Boussaid, H. Laga, and M. Bennamoun,
“Hands-on bayesian neural networks–a tutorial for deep learning users,”
arXiv preprint arXiv:2007.06823, 2020.
CR  - [18] S. Sharma, S. Sharma, and A. Athaiya, “Activation functions in neural
networks,” Towards Data Sci, vol. 6, no. 12, pp. 310–316, 2017.
CR  - [19] D. Liberzon, Switching in systems and control, vol. 190. Springer, 2003.
CR  - [20] R. Goebel, R. G. Sanfelice, and A. R. Teel, “Hybrid dynamical systems,”
IEEE control systems magazine, vol. 29, no. 2, pp. 28–93, 2009.
CR  - [21] B. Brogliato and B. Brogliato, Nonsmooth mechanics. Springer, 1999.
CR  - [22] S. Ross, G. J. Gordon, and J. A. Bagnell, “No-regret reductions for
imitation learning and structured prediction,” in In AISTATS, Citeseer,
2011.
CR  - [23] J. Revels, M. Lubin, and T. Papamarkou, “Forward-mode automatic
differentiation in julia,” arXiv preprint arXiv:1607.07892, 2016.
CR  - [24] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,”
arXiv preprint arXiv:1412.6980, 2014.
CR  - [25] D.-A. Clevert, T. Unterthiner, and S. Hochreiter, “Fast and accurate
deep network learning by exponential linear units (elus),” arXiv preprint
arXiv:1511.07289, 2015.
CR  - [26] J. J. Moreau, “Unilateral contact and dry friction in finite freedom
dynamics,” Nonsmooth mechanics and Applications, pp. 1–82, 1988.
CR  - [27] C. Glocker and C. Studer, “Formulation and preparation for numerical
evaluation of linear complementarity systems in dynamics,” Multibody
System Dynamics, vol. 13, pp. 447–463, 2005.
CR  - [28] V. Acary and B. Brogliato, Numerical methods for nonsmooth dynamical
systems: applications in mechanics and electronics. Springer Science &
Business Media, 2008.
CR  - [29] Quanser, Linear Servo Base Unit with Inverted Pendulum. Apr 2021.
CR  - [30] M. Spong, S. Hutchinson, and M. Vidyasagar, Robot Modeling and
Control. Wiley, 2020.
CR  - [31] H. Khalil, Nonlinear Control. Always Learning, Pearson, 2015.
UR  - https://doi.org/10.17694/bajece.1515854
L1  - https://dergipark.org.tr/en/download/article-file/4069126
ER  -