Reactive execution for solving plan failures in planning control applications

Guzmán, C.; Castejon, Pablo; Onaindía, Eva; Frank, Jeremy

doi:10.3233/ica-150493

Cited by 10 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a centralized control system, one central controller uses the global measurement data collected from all the sensors installed in the structure (which are usually on different floors in two principal directions) to make control decisions and dispatches those decisions to control devices [22][23][24]. In such a system, the requirements on communication range and data transmission bandwidth increase with the size of the structure and the number of sensors and control devices deployed.…”

Section: Generalmentioning

confidence: 99%

Multi-agent replicator controller for sustainable vibration control of smart structures

Soto¹,

Adeli²

2017

J. vibroeng.

View full text Add to dashboard Cite

Developed in the artificial intelligence community, an intelligent agent is an autonomous abstract or software entity that observes through sensors and acts upon an environment in an adaptive or intelligent manner. In a centralized control system, one central controller uses the global measurement data collected from all the sensors installed in the structure to make control decisions and to dispatch them to control devices. The centralized controller itself represents a single point of potential failure. To overcome this shortcoming, decentralized control is used to improve redundancy. This paper introduces three ideas to vibration control of smart structures: agent technology, replicator dynamics from evolutionary game theory, and energy minimization. It presents two new methods: 1) a single-agent Centralized Replicator Controller (CRC) and a decentralized Multi-Agent Replicator Controller (MARC) for vibration control of smart structures. The use of agents and a decentralized approach enhances the robustness of the entire vibration control system. The proposed control methodologies are applied to vibration control of a 3-story steel frame and a 20-story steel benchmark structure subjected to two sets of seismic loadings: historic earthquake accelerograms and artificial earthquakes and compared with the corresponding centralized and decentralized conventional Linear Quadratic Regulator (LQR) control algorithm.

show abstract

Section: Generalmentioning

confidence: 99%

Multi-agent replicator controller for sustainable vibration control of smart structures

Soto¹,

Adeli²

2017

J. vibroeng.

View full text Add to dashboard Cite

show abstract

“…Compared with planning or replanning, plan repair is more prevalent in plan failure handling due to its shorter solution time [22,23]. There is much research work on plan repair in the literature, which can be roughly divided into five categories [24]: the rule matching method [25], the local adjustment method [26], the unrefinement and refinement method [27], the state transition method [28] and the new problem construction method [29,30]. However, most of these seem to assume that the agent keeps static when resuming the failed plan, which is discontinuous.…”

Section: Related Workmentioning

confidence: 99%

“…The same idea as Guzman [28], but we added the processing of durable, concurrent, and resource-dependent actions. We also implemented it on POPF2).…”

Section: Setup Of the Experimentsmentioning

confidence: 99%

Autonomous Recovery from Spacecraft Plan Failures by Regulatory Repair While Retaining Operability

Cui

et al. 2022

Aerospace

View full text Add to dashboard Cite

Pre-designed spacecraft plans suffer from failure due to the uncertain space environment. In this case, instead of spending a long time waiting for ground control to upload a feasible plan in order to achieve the mission goals, the spacecraft could repair the failed plan while executing another part of the plan. This paper proposes a method called Isolation and Repair Plan Failures (IRPF) for a spaceship with durable, concurrent, and resource-dependent actions. To enable the spacecraft to perform some actions when a plan fails, IRPF separates all defective actions from executable actions in the pre-designed plan according to causal analysis between the failure state and the established plan. Then, to address the competition between operation and repair during the partial execution of the plan, IRPF sets up several regulatory factors associated with the search process for a solution, and then repairs the broken plan within the limits of these factors. Experiments were carried out in simulations of a satellite and a multi-rover system. The results demonstrate that, compared with replanning and other plan-repair methods, IRPF creates an execution plan more quickly and searches for a recovery plan with fewer explored state nodes in a shorter period of time.

show abstract

“…Artificial Intelligence techniques are helping industries to improve their efficiency and performance in a great variety of applications: education Rani et al [8], space Tonutti et al [11], He et al [6], space exploration Guzman et al [5], manufacturing Wilson [12], Rao et al [9], etc. The development of a computer program, that employs artificial intelligence techniques to predict the values of the physical properties of the materials mentioned above without having to resort to the elaboration of the physical parts of biodegradable thermoplastic starch, will be a great utility to extend its industrial application: allowing to reduce time, resources and costs.…”

Section: Introductionmentioning

confidence: 99%

Predicting mechanical properties of thermoplastic starch films with artificial intelligence techniques

Guzmán¹,

Collazo‐Bigliardi²,

Ortega‐Toro³

2018

ces

Self Cite

View full text Add to dashboard Cite

Biodegradable polymers have similar physicochemical properties than conventional polymers, but they can be degradable under controlled conditions in less than 180 days. Thermoplastic starch films have a relative importance because of their low cost, high production and good processability by conventional techniques like melt blending, compression molding, extrusion, among others. However, they present several drawbacks (poor mechanical properties, high water vapor permeability, and retrogradation) that limit their industrial applications. In the present paper, we developed a computer tool, which employs artificial

show abstract

Reactive execution for solving plan failures in planning control applications

Cited by 10 publications

References 33 publications

Multi-agent replicator controller for sustainable vibration control of smart structures

Multi-agent replicator controller for sustainable vibration control of smart structures

Autonomous Recovery from Spacecraft Plan Failures by Regulatory Repair While Retaining Operability

Predicting mechanical properties of thermoplastic starch films with artificial intelligence techniques

Contact Info

Product

Resources

About