Event-triggered Pulse Control with Model Learning (if Necessary)

Baurnann, Dominik; Solowjow, Friedrich; Johansson, Karl Henrik; Trimpe, Sebastian

doi:10.23919/acc.2019.8814333

Cited by 8 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although learning methods have the potential to increase system performance, performing a learning task is costly itself (e.g., including communication resources and computation cost). Therefore, some articles [11], [13], [14] consider event-triggering rules for model learning which decides when a new model should learn based on statistical properties of inter-communication time. These articles construct learning trigger based on deriving model-induced probability distribution and observing inter-communication times.…”

Section: Machine Learning In Model-based Event Triggered Controlmentioning

confidence: 99%

“…An event-triggered pulse control strategy is combined with SL in [14] to learn a dynamic model as shown in Fig. 3.…”

Section: Machine Learning In Model-based Event Triggered Controlmentioning

confidence: 99%

“…Although learning is critical for autonomous systems that are facing uncertainties and changing environments, the process of learning a new model or behaviour involves a certain cost. Therefore, the question of when to learn is considered in [13], [14] to trade off between a better response and the cost of learning. Different ML algorithms are under consideration in which the control system is continuously learning from the dynamics of the overall system and its environment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning in Event-Triggered Control: Recent Advances and Open Issues

Sedghi¹,

Ijaz²,

Noor-A-Rahim³

et al. 2020

Preprint

View full text Add to dashboard Cite

Network Control Systems (NCSs) have attracted much interest over the past decade as part of a move towards more decentralised control applications and the rise of cyberphysical system applications. Many practical NCSs face the challenges of limited communication bandwidth resources, reliability and lack of knowledge of network dynamics, particularly when wireless networks are involved. Machine learning (ML) combined with event-triggered control (ETC) has the potential to ease some of these challenges. For example, ML can be used to overcome the problem of a lack of network models by learning system behaviour or adapt to dynamically changing models by continually learning model dynamics. ETC can help to conserve bandwidth resources by communicating only when needed or when resources are available. Here, we present a review of the literature on work that combines ML and ETC. The literature on supervised, semi-supervised, unsupervised and reinforcement learning based approaches such as deep reinforcement learning and statistical learning in combination with ETC is explored. Furthermore, the difference between the application of these learning algorithms on model-based and model-free systems are discussed. Following the analysis of the literature, we highlight open research questions and challenges related to ML-based ETC and propose approaches to possible solutions to these challenges.

show abstract

Section: Machine Learning In Model-based Event Triggered Controlmentioning

confidence: 99%

“…An event-triggered pulse control strategy is combined with SL in [14] to learn a dynamic model as shown in Fig. 3.…”

Section: Machine Learning In Model-based Event Triggered Controlmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Event-Triggered Control: Recent Advances and Open Issues

Sedghi¹,

Ijaz²,

Noor-A-Rahim³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The probabilistic priority measure proposed herein is represented by the probability of communicating at a horizon, and is derived according to the exit times of stochastic processes. Exit/stopping time analysis has been applied to arrive at optimal communication decisions in Xu and Hespanha (2004); Rabi et al (2008), while Baumann et al (2019) and Solowjow et al (2018) use such analysis to evaluate model performance and trigger learning experiments. However, neither design considers predicting future communications with limited resources.…”

Section: Contributionsmentioning

confidence: 99%

Predictive Triggering for Distributed Control of Resource Constrained Multi-agent Systems

2019

Self Cite

View full text Add to dashboard Cite

A predictive triggering (PT) framework for the distributed control of resource constrained multi-agent systems is proposed. By predicting future communication demands and deriving a probabilistic priority measure, the PT framework is able to allocate limited communication resources in advance. The framework is evaluated through simulations of a cooperative adaptive cruise control system and experiments on multi-agent cart-pole systems. The results of these studies show its effectiveness over other event-triggered designs at reducing network utilization, while also improving the control error of the system.

show abstract

“…On physical systems, data are often sparse because the data collection is subject to life‐time and cost constraints. While it has been proposed to identify structural knowledge directly from data [7,80], the identification of structure requires significant amounts of data. In the next section, we detail our understanding of structure, and why it is beneficial to combine analytical structure with data‐driven modeling.…”

Section: Introductionmentioning

confidence: 99%

Structured learning of rigid‐body dynamics: A survey and unified view from a robotics perspective

Geist

Trimpe

2021

GAMM-Mitteilungen

Self Cite

View full text Add to dashboard Cite

Accurate models of mechanical system dynamics are often critical for model‐based control and reinforcement learning. Fully data‐driven dynamics models promise to ease the process of modeling and analysis, but require considerable amounts of data for training and often do not generalize well to unseen parts of the state space. Combining data‐driven modeling with prior analytical knowledge is an attractive alternative as the inclusion of structural knowledge into a regression model improves the model's data efficiency and physical integrity. In this article, we survey supervised regression models that combine rigid‐body mechanics with data‐driven modeling techniques. We analyze the different latent functions (such as kinetic energy or dissipative forces) and operators (such as differential operators and projection matrices) underlying common descriptions of rigid‐body mechanics. Based on this analysis, we provide a unified view on the combination of data‐driven regression models, such as neural networks and Gaussian processes, with analytical model priors. Furthermore, we review and discuss key techniques for designing structured models such as automatic differentiation.

show abstract

Event-triggered Pulse Control with Model Learning (if Necessary)

Cited by 8 publications

References 22 publications

Machine Learning in Event-Triggered Control: Recent Advances and Open Issues

Machine Learning in Event-Triggered Control: Recent Advances and Open Issues

Predictive Triggering for Distributed Control of Resource Constrained Multi-agent Systems

Structured learning of rigid‐body dynamics: A survey and unified view from a robotics perspective

Contact Info

Product

Resources

About