Distributed Bayesian Online Learning for Cooperative Manipulation

For tasks where the dynamics of multiple agents are physically coupled, e.g., in cooperative manipulation, the coordination between the individual agents becomes crucial, which requires exact knowledge of the interaction dynamics. This problem is typically addressed using centralized estimators, which can negatively impact the flexibility and robustness of the overall system. To overcome this shortcoming, we propose a novel distributed learning framework for the exemplary task of cooperative manipulation using Bayesian principles. Using only local state information each agent obtains an estimate of the object dynamics and grasp kinematics. These local estimates are combined using dynamic average consensus. Due to the strong probabilistic foundation of the method, each estimate of the object dynamics and grasp kinematics is accompanied by a measure of uncertainty, which allows to guarantee a bounded prediction error with high probability. Moreover, the Bayesian principles directly allow iterative learning with constant complexity, such that the proposed learning method can be used online in real-time applications. The effectiveness of the approach is demonstrated in a simulated cooperative manipulation task.

[1]  David J. Fleet,et al.  Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictions , 2014, ArXiv.

[2]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[3]  P. Chiacchio,et al.  Six-DOF Impedance Control of Dual-Arm Cooperative Manipulators , 2008, IEEE/ASME Transactions on Mechatronics.

[4]  René Vidal,et al.  Distributed image-based 3-D localization of camera sensor networks , 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

[5]  L. Fahrmeir,et al.  Regression - Modelle, Methoden und Anwendungen , 2009 .

[6]  Juraj Kabzan,et al.  Cautious Model Predictive Control Using Gaussian Process Regression , 2017, IEEE Transactions on Control Systems Technology.

[7]  Dana Kulic,et al.  Stable Gaussian Process based Tracking Control of Euler-Lagrange Systems , 2018, Autom..

[8]  Aditya Gopalan,et al.  On Kernelized Multi-armed Bandits , 2017, ICML.

[9]  Senior Member,et al.  Model and analysis of the interaction dynamics in cooperative manipulation tasks , 2016 .

[10]  Antonio Franchi,et al.  Decentralized parameter estimation and observation for cooperative mobile manipulation of an unknown load using noisy measurements , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Alessandro Marino,et al.  Distributed Adaptive Control of Networked Cooperative Mobile Manipulators , 2018, IEEE Transactions on Control Systems Technology.

[12]  Sandra Hirche,et al.  Estimating unknown object dynamics in human-robot manipulation tasks , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[13]  F. Rubio,et al.  On the existence of a normal approximation to the distribution of the ratio of two independent normal random variables , 2013 .

[14]  Marc Peter Deisenroth,et al.  Distributed Gaussian Processes , 2015, ICML.

[15]  Sandra Hirche,et al.  Localized active learning of Gaussian process state space models , 2020, L4DC.

[16]  Francesco Pierri,et al.  Cooperative Manipulation of an Unknown Object via Omnidirectional Unmanned Aerial Vehicles , 2020, J. Intell. Robotic Syst..

[17]  Sandra Hirche,et al.  Distributed Control for Cooperative Manipulation With Event-Triggered Communication , 2020, IEEE Transactions on Robotics.

[18]  G. Alefeld,et al.  Interval analysis: theory and applications , 2000 .

[19]  Sonia Martínez,et al.  Discrete-time dynamic average consensus , 2010, Autom..

[20]  Giuseppe Muscio,et al.  Distributed cooperative object parameter estimation and manipulation without explicit communication , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Emilio Tanowe Maddalena,et al.  Deterministic error bounds for kernel-based learning techniques under bounded noise , 2020, Autom..