arXiv subjects

Martin Guay

Publications and source records attributed to Martin Guay.

28 records · Page 2Linked to original sources

arXiv2025

Strategic learning for disturbance rejection in multi-agent systems: Nash and Minmax in graphical games

This article investigates the optimal control problem with disturbance rejection for discrete-time multi-agent systems under cooperative and non-cooperative graphical games frameworks. Given the practical challenges of obtaining accurate models, Q-function-based policy iteration methods are proposed to seek the Nash equilibrium solution for the cooperative graphical game and the distributed minmax solution for the non-cooperative graphical game. To implement these methods online, two reinforcement learning frameworks are developed, an actor-disturber-critic structure for the cooperative graphical game and an actor-adversary-disturber-critic structure for the non-cooperative graphical game. The stability of the proposed methods is rigorously analyzed, and simulation results are provided to illustrate the effectiveness of the proposed methods.

eess.SY↗

arXiv2024

Generalized Pose Space Embeddings for Training In-the-Wild using Anaylis-by-Synthesis

Modern pose estimation models are trained on large, manually-labelled datasets which are costly and may not cover the full extent of human poses and appearances in the real world. With advances in neural rendering, analysis-by-synthesis and the ability to not only predict, but also render the pose, is becoming an appealing framework, which could alleviate the need for large scale manual labelling efforts. While recent work have shown the feasibility of this approach, the predictions admit many flips due to a simplistic intermediate skeleton representation, resulting in low precision and inhibiting the acquisition of any downstream knowledge such as three-dimensional positioning. We solve this problem with a more expressive intermediate skeleton representation capable of capturing the semantics of the pose (left and right), which significantly reduces flips. To successfully train this new representation, we extend the analysis-by-synthesis framework with a training protocol based on synthetic data. We show that our representation results in less flips and more accurate predictions. Our approach outperforms previous models trained with analysis-by-synthesis on standard benchmarks.

cs.CV↗

arXiv2024

A nonparametric learning framework for nonlinear robust output regulation

A nonparametric learning solution framework is proposed for the global nonlinear robust output regulation problem. We first extend the assumption that the steady-state generator is linear in the exogenous signal to the more relaxed assumption that it is polynomial in the exogenous signal. Additionally, a nonparametric learning framework is proposed to eliminate the construction of an explicit regressor, as required in the adaptive method, which can potentially simplify the implementation and reduce the computational complexity of existing methods. With the help of the proposed framework, the robust nonlinear output regulation problem can be converted into a robust non-adaptive stabilization problem for the augmented system with integral input-to-state stable (iISS) inverse dynamics. Moreover, a dynamic gain approach can adaptively raise the gain to a sufficiently large constant to achieve stabilization without requiring any a priori knowledge of the uncertainties appearing in the dynamics of the exosystem and the system. Furthermore, we apply the nonparametric learning framework to globally reconstruct and estimate multiple sinusoidal signals with unknown frequencies without the need for adaptive parametric techniques. An explicit nonlinear mapping can directly provide the estimated parameters, which will exponentially converge to the unknown frequencies. Finally, a feedforward control design is proposed to solve the linear output regulation problem using the nonparametric learning framework. Two simulation examples are provided to illustrate the effectiveness of the theoretical results.

eess.SY↗

arXiv2024

Distributed State Estimation for Linear Time-invariant Systems with Aperiodic Sampled Measurement

This paper deals with the state estimation of linear time-invariant systems using distributed observers with local sampled-data measurement and aperiodic communication. Each observer agent perceives partial information of the system to be observed but does not satisfy the observability condition. Consequently, distributed observers are designed to exponentially estimate the state of the system to be observed by time-varying sampling and asynchronous communication. Additionally, explicit upper bounds on allowable sampling periods for convergent estimation errors are given. Finally, a numerical example is provided to demonstrate the validity of the theoretical results

eess.SY↗

arXiv2024

Prescribed Time Dual-Mode Extremum Seeking Control

We propose a dual mode extremum seeking control design technique that achieves real-time optimization of an unknown measured cost function in a prescribed time. The controller is shown to achieve semi-global practical stability of the optimal equilibrium for the state variables and the input variable for a class of nonlinear dynamical control systems with unknown dynamics. The design technique proposes a timescale transformation that enables the use of dither signals with increasing frequencies. The proposed timescale transformation is designed to avoid the singularity occurring at the prescribed time. A simulation study is performed to demonstrate the effectiveness of the proposed technique.

math.OC↗

arXiv2023

Distributed State Estimation for Jointly Observable Linear Systems over Time-varying Networks

This paper deals with a distributed state estimation problem for jointly observable multi-agent systems operated over various time-varying network topologies. The results apply when the system matrix of the system to be observed contains eigenvalues with positive real parts. They also can apply to situations where the communication networks are disconnected at every instant. We present sufficient conditions for the existence of distributed observers for general linear systems over periodic communication networks. Using an averaging approach, it is shown that the proposed distributed observer can provide exponentially converging state estimates of the state of the linear system when the network is uniformly connected on average. This average connectedness condition offers a more relaxed assumption that includes periodic switching, Markovian switching and Cox process switching as special cases. All the agents in the network share the estimated state with their neighbours through the network and cooperatively reconstruct the entire state locally. Furthermore, this study presents two exponential stability results for two classes of switched systems, providing valuable tools in related distributed state estimation approaches. A toy example and three practical applications are provided to illustrate the effectiveness of the theoretical results.

eess.SY↗

arXiv2023

Nonlinear Bipartite Output Regulation with Application to Turing Pattern

In this paper, a bipartite output regulation problem is solved for a class of nonlinear multi-agent systems subject to static signed communication networks. A nonlinear distributed observer is proposed for a nonlinear exosystem with cooperation-competition interactions to address the problem. Sufficient conditions are provided to guarantee its existence and stability. The exponential stability of the observer is established. As a practical application, a leader-following bipartite consensus problem is solved for a class of nonlinear multi-agent systems based on the observer. Finally, a network of multiple pendulum systems is treated to support the feasibility of the proposed design. The possible application of the approach to generate specific Turing patterns is also presented.

math.OC↗

arXiv2020

Finite-time Newton seeking control

This paper proposes a finite-time Newton seeking control design for systems described by unknown multivariable static maps. The Newton seeking system has an averaged system that implements a Newton continuous-time algorithm. The averaged Newton seeking system is shown to achieve finite-time stability of the unknown optimum of the static map. An averaging analysis demonstrates that the proposed Newton-seeking achieves finite-time practical stability of the optimum. A simulation study is used to demonstrate the effectiveness of the design method.

math.OC↗

arXiv2020

Rig-space Neural Rendering

Movie productions use high resolution 3d characters with complex proprietary rigs to create the highest quality images possible for large displays. Unfortunately, these 3d assets are typically not compatible with real-time graphics engines used for games, mixed reality and real-time pre-visualization. Consequently, the 3d characters need to be re-modeled and re-rigged for these new applications, requiring weeks of work and artistic approval. Our solution to this problem is to learn a compact image-based rendering of the original 3d character, conditioned directly on the rig parameters. Our idea is to render the character in many different poses and views, and to train a deep neural network to render high resolution images, from the rig parameters directly. Many neural rendering techniques have been proposed to render from 2d skeletons, or geometry and UV maps. However these require manual work, and to do not remain compatible with the animator workflow of manipulating rig widgets, as well as the real-time game engine pipeline of interpolating rig parameters. We extend our architecture to support dynamic re-lighting and composition with other 3d objects in the scene. We designed a network that efficiently generates multiple scene feature maps such as normals, depth, albedo and mask, which are composed with other scene objects to form the final image.

cs.GR↗

arXiv2019

Animating an Autonomous 3D Talking Avatar

One of the main challenges with embodying a conversational agent is annotating how and when motions can be played and composed together in real-time, without any visual artifact. The inherent problem is to do so---for a large amount of motions---without introducing mistakes in the annotation. To our knowledge, there is no automatic method that can process animations and automatically label actions and compatibility between them. In practice, a state machine, where clips are the actions, is created manually by setting connections between the states with the timing parameters for these connections. Authoring this state machine for a large amount of motions leads to a visual overflow, and increases the amount of possible mistakes. In consequence, conversational agent embodiments are left with little variations and quickly become repetitive. In this paper, we address this problem with a compact taxonomy of chit chat behaviors, that we can utilize to simplify and partially automate the graph authoring process. We measured the time required to label actions of an embodiment using our simple interface, compared to the standard state machine interface in Unreal Engine, and found that our approach is 7 times faster. We believe that our labeling approach could be a path to automated labeling: once a sub-set of motions are labeled (using our interface), we could learn a prediction that could attribute a label to new clips---allowing to really scale up virtual agent embodiments.

cs.HC↗