Consensus for black-box nonlinear agents using optimistic optimization

An important problem in multiagent systems is consensus, which requires the agents to agree on certain controlled variables of interest. We focus on the challenge of dealing in a generic way with nonlinear agent dynamics, represented as a black box with unknown mathematical form. Our approach designs a reference behavior with a classical consensus method. The main novelty is using optimistic optimization (OO) to find controls that closely follow the reference behavior. The first advantage of OO is that it only needs to sample the black-box model of the agent, and so achieves our goal of handling unknown nonlinearities. Secondly, a tight relationship is guaranteed between computation invested and closeness to the reference behavior. Our main results exploit these properties to prove practical consensus. An analysis of representative examples builds additional insight and shows that in some nontrivial problems the optimization is easy to solve by OO. Simulations on these examples accompany the analysis.

[1]  Jessy W. Grizzle.  A linear algebraic framework for the analysis of discrete-time nonlinear systems , 1993 .

[2]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[3]  John N. Tsitsiklis,et al.  Distributed Asynchronous Deterministic and Stochastic Gradient Optimization Algorithms , 1984, 1984 American Control Conference.

[4]  Reza Olfati-Saber,et al.  Flocking for multi-agent dynamic systems: algorithms and theory , 2006, IEEE Transactions on Automatic Control.

[5]  Rémi Munos,et al.  From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning , 2014, Found. Trends Mach. Learn..

[6]  George J. Pappas,et al.  Flocking in Teams of Nonholonomic Agents , 2003 .

[7]  Rémi Munos,et al.  Optimistic Optimization of Deterministic Functions , 2011, NIPS 2011.

[8]  Guangfu Ma,et al.  Distributed Coordinated Tracking With a Dynamic Leader for Multiple Euler-Lagrange Systems , 2011, IEEE Transactions on Automatic Control.

[9]  F.L. Lewis,et al.  Reinforcement learning and adaptive dynamic programming for feedback control , 2009, IEEE Circuits and Systems Magazine.

[10]  Guanrong Chen,et al.  Adaptive second-order consensus of networked mobile agents with nonlinear dynamics , 2011, Autom..

[11]  Wenwu Yu,et al.  Flocking of multi-agent dynamical systems based on pseudo-leader mechanism , 2009, Syst. Control. Lett..

[12]  Michel Fliess,et al.  Reversible linear and nonlinear discrete-time dynamics , 1992 .

[13]  Stefan Edelkamp,et al.  Heuristic Search - Theory and Applications , 2011 .

[14]  John N. Tsitsiklis,et al.  Convergence Speed in Distributed Consensus and Averaging , 2009, SIAM J. Control. Optim..

[15]  George Meyer,et al.  Stable inversion for nonlinear systems , 1997, Autom..

[16]  Stephen P. Boyd,et al.  Fast linear iterations for distributed averaging , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[17]  Randal W. Beard,et al.  Distributed Consensus in Multi-vehicle Cooperative Control - Theory and Applications , 2007, Communications and Control Engineering.

[18]  Lucian Buşoniu,et al.  Optimistic Planning for Consensus , 2013 .

[19]  Zhihua Qu,et al.  Cooperative Control of Dynamical Systems With Application to Autonomous Vehicles , 2008, IEEE Transactions on Automatic Control.

[20]  Karl Henrik Johansson,et al.  A Study On Distributed Model Predictive Consensus , 2008, ArXiv.

[21]  Robin J. Evans,et al.  MINIMAL ORDER DISCRETE-TIME NONLINEAR SYSTEM INVERSION , 2002 .

[22]  Richard M. Murray,et al.  Consensus problems in networks of agents with switching topology and time-delays , 2004, IEEE Transactions on Automatic Control.

[23]  Bernard Widrow,et al.  Adaptive Inverse Control: A Signal Processing Approach , 2007 .

[24]  Randal W. Beard,et al.  Consensus-based Design Methodologies for Distributed Multivehicle Cooperative Control , 2008 .

[25]  Eduardo Sontag,et al.  Controllability of Nonlinear Discrete-Time Systems: A Lie-Algebraic Approach , 1990, SIAM Journal on Control and Optimization.

[26]  Z. Qu,et al.  Cooperative Control of Dynamical Systems: Applications to Autonomous Vehicles , 2009 .

[27]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[28]  Reza Olfati-Saber,et al.  Consensus and Cooperation in Networked Multi-Agent Systems , 2007, Proceedings of the IEEE.

[29]  Luc Moreau,et al.  Stability of multiagent systems with time-dependent communication links , 2005, IEEE Transactions on Automatic Control.

[30]  Randal W. Beard,et al.  Consensus seeking in multiagent systems under dynamically changing interaction topologies , 2005, IEEE Transactions on Automatic Control.

[31]  Feng Ding,et al.  Identification of Hammerstein nonlinear ARMAX systems , 2005, Autom..

[32]  Wim Michiels,et al.  Consensus Problems with Distributed Delays, with Application to Traffic Flow Models , 2009, SIAM J. Control. Optim..

[33]  Riccardo Scattolini,et al.  Model Predictive Control Schemes for Consensus in Multi-Agent Systems with Single- and Double-Integrator Dynamics , 2009, IEEE Transactions on Automatic Control.

[34]  Lucian Busoniu,et al.  Consensus for agents with general dynamics using optimistic optimization , 2013, 52nd IEEE Conference on Decision and Control.

[35]  J. Massey,et al.  Invertibility of linear time-invariant dynamical systems , 1969 .

[36]  Johan A. K. Suykens,et al.  Nonlinear modeling : advanced black-box techniques , 1998 .

[37]  P.J. Antsaklis,et al.  Asynchronous Consensus Protocols: Preliminary Results, Simulations and Open Questions , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.