Distributed, autonomous control of Space habitats

Kortenkamp, D.; Bonasso, R. Peter; Subramanian, Devika

doi:10.1109/aero.2001.931296

Cited by 6 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we extend previous work [23] by performing a detailed comparison of genetic algorithm (GA) and stochastic hill-climbing (SH) approaches to ALSS control. Evaluation of candidate solutions is performed on a newer and more complete ALSS model than was previously available.…”

mentioning

confidence: 90%

“…We have implemented an ALSS simulator that models the basic processes occurring in the Bioregenerative Planetary Life Support System Test Complex (BIO-Plex) developed by NASA Johnson Space Center [4], [23], [38]. This simulator is used to evaluate the candidate control strategies generated by our algorithm.…”

Section: A Alss Simulatormentioning

confidence: 99%

“…Kortenkamp et al [23] are the first to evaluate ML methods for learning effective ALSS energy allocations using an early version of the BIO-Plex simulation. They find both the GA and reinforcement learning to be viable choices for maximizing either or both the mission duration and productivity of a single simulator run.…”

Section: B Related Workmentioning

confidence: 99%

“…While deliberative control systems may suffice under static conditions, some element of learning or adaptability is likely to be necessary in real world scenarios. Kortenkamp et al [23] present the first study that successfully uses machine learning (ML) techniques to learn how to control an ALSS as a whole.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Intelligent Automated Control of Life Support Systems Using Proportional Representations

Garibay²

2004

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

Abstract-Effective automatic control of Advanced Life Support Systems (ALSS) is a crucial component of space exploration. An ALSS is a coupled dynamical system which can be extremely sensitive and difficult to predict. As a result, such systems can be difficult to control using deliberative and deterministic methods. We investigate the performance of two machine learning algorithms, a genetic algorithm (GA) and a stochastic hill-climber (SH), on the problem of learning how to control an ALSS, and compare the impact of two different types of problem representations on the performance of both algorithms. We perform experiments on three ALSS optimization problems using five strategies with multiple variations of a proportional representation for a total of 120 experiments. Results indicate that although a proportional representation can effectively boost GA performance, it does not necessarily have the same effect on other algorithms such as SH. Results also support previous conclusions [23] that multivector control strategies are an effective method for control of coupled dynamical systems.

show abstract

mentioning

confidence: 90%

Section: A Alss Simulatormentioning

confidence: 99%

Section: B Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Intelligent Automated Control of Life Support Systems Using Proportional Representations

Garibay²

2004

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

show abstract

“…In closed-loop life support systems there are complex interactions between sub-systems such as air, water, food production, solids processing, and the crew. Recent research at NASA Johnson Space Center has led to significant insights into autonomous control of ALS systems [1,2,3]. Routine control of an ALS system is well within the reach of current techniques.…”

Section: Introductionmentioning

confidence: 99%

Planner-Based Control of Advanced Life Support Systems

Muscettola¹,

Kortenkamp²,

Fry³

et al. 2005

SAE Technical Paper Series

View full text Add to dashboard Cite

The paper describes an approach to the integration of qualitative and quantitative modeling techniques for advanced life support (ALS) systems.Developing reliable control strategies that scale up to fully integrated life support systems requires augmenting quantitative models and control algorithms with the abstractions provided by qualitative, symbolic models and their associated high-level control strategies. This will allow for effective management of the combinatorics that emerge when integrating a large number of ALS subsystems. By focusing control actions at different levels of detail and reactivity we can use faster, simpler responses at the lowest level and predictive but complex responses at the higher levels of abstraction.In particular, methods from model-based planning and scheduling can provide optimal resource management over long time periods. We describe a reference implementation of an advanced control system using the IDEA control architecture developed at NASA Ames Research Center. IDEA uses planning/scheduling as the sole reasoning method for predictive and reactive closed loop control.We describe preliminary experiments in planner-based control of ALS carried out on an integrated ALS simulation developed at NASA Johnson Space Center.

show abstract

Interactive Multi-Modal Robot Programming

Iba

Paredis

Khosla

2006

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

The goal of the Interactive Multi-Modal Robot Programming system is a comprehensive human-machine interface that allows non-experts to compose robot programs conveniently. Two key characteristics of this novel programming approach are that the user can provide feedback interactively at any time through an intuitive interface and that the system infers the user's intent to support interaction. The framework takes a three-step approach to the problem: multi-modal recognition, intention interpretation, and prioritized task execution. The system is demonstrated by interactively controlling and programming a mobile vacuum cleaning robot. The demonstrations are used to exemplify the interactive programming and plan recognition aspects of the research.

show abstract

Distributed, autonomous control of Space habitats

Cited by 6 publications

References 4 publications

Intelligent Automated Control of Life Support Systems Using Proportional Representations

Intelligent Automated Control of Life Support Systems Using Proportional Representations

Planner-Based Control of Advanced Life Support Systems

Interactive Multi-Modal Robot Programming

Contact Info

Product

Resources

About