Genetics-Based Machine Learning Approach for Rule Acquisition in an AGV Transportation System

Sakakibara, Kazutoshi; Fukui, Yoshiro; Nishikawa, Ikuko

doi:10.1109/isda.2008.329

Cited by 7 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A simulation is run offline that evaluates different re-routing rules and generates training examples that map the best performing rule to a given conflict situation. Further applications of the approach are detailed in Sakakibara et al (2008), Aufenanger et al (2008), Kwak and Yih (2004), Klaas et al (2011) and (Piramuthu et al (1993).…”

Section: Related Workmentioning

confidence: 99%

“…Knowledge-based methods are a class of heuristics and are able to adapt to changes in the patterns of external requests by modifying the accumulated knowledge. Recently, knowledge-based methods have been applied to these problems that combine methods of artificial intelligence with simulation, including Sakakibara et al (2008), Kwak and Yih (2004), Aufenanger et al (2008). The control problem is posed as the decision to choose from a predefined set of actions (eg different ways to sort the available storage spaces) considering the current situation, which includes all information relevant to the decision.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using simulation as an adaptive source of knowledge for the control of material handling systems

Klaas

Laroque

Renken

et al. 2016

Journal of Simulation

View full text Add to dashboard Cite

Recent advances in computing have allowed simulation to be used as a source of data in the real-time control of logistics systems such as Material Handling Systems (MHS). For a real-world MHS, in development by Lödige Industries GmbH, Germany, we demonstrate the benefit of generating data offline using a parametrized simulation model that real-time operational control is based on. The data consist of mappings of control situations to optimal actions respectively. Our approach allows for self-adaptation of the simulation by observing current system parameters that are fed into the model. The control automatically triggers regeneration when necessary, detects changes in the system and also proactively anticipates them, resulting in consistently high performance. We furthermore use a simulation-based look-ahead method to consider uncertainties when evaluating alternative actions. Evaluation results show a significant increase in system performance compared to fixed application of a control action and demonstrate the benefits of the self-adaptive properties.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using simulation as an adaptive source of knowledge for the control of material handling systems

Klaas

Laroque

Renken

et al. 2016

Journal of Simulation

View full text Add to dashboard Cite

show abstract

“…When simulating in an off-line phase, rather than on-line, runtime constraints are much weaker and thus has been done in works such as Sakakibara, Fukui, and Nishikawa (2008), Aufenanger et al (2008), Kwak and Yih (2004), Klaas et al (2011). The idea is always to simulate the controlled system in advance of application under the expected circumstances and consequently using the generated data in on-line decision making.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, knowledge based methods have been applied to these problems that combine methods of artificial intelligence with simulation, including (Sakakibara, Fukui, and Nishikawa 2008;Kwak and Yih 2004;Aufenanger et al 2008). Simulation is used in an off-line phase as a source of knowledge, as control situations can be solved and the results stored as training examples.…”

Section: Introductionmentioning

confidence: 99%

Simulation aided, self-adapting knowledge based control of material handling systems

Klaas

Laroque

Renken

et al. 2013

2013 Winter Simulations Conference (WSC)

View full text Add to dashboard Cite

Knowledge based methods have recently been applied to the control of material handling systems, specifically using simulation as a source of knowledge. Little research has been done however on ensuring a consistently high quality of the data generated by the simulation, especially under changing circumstances such as differing load patterns in the system. We propose a self-adapting control that is able to automatically generate knowledge according to current circumstances using a parametrized simulation model, which uses observed system parameters as input. The control automatically triggers generation when necessary, detects changes in the system and also proactively anticipates them, resulting in consistently high performance. For the problem of knowledge generation (determining an optimal control action to a given situation), we present a look ahead simulation method that considers uncertainties. We validated our approach in a real world material handling system, developed by Lödige Industries GmbH.

show abstract

“…An augmented Lagrangian decomposition [12] and coordination technique are used to minimize the total transportation time. Reference [13] proposed an autonomous decentralized method for multiple automated guided vehicles (AGVs) static route planning. Discrete particle swarm optimization (DPSO) [14] was considered an efficient method to solve route planning problem.…”

Section: Introductionmentioning

confidence: 99%

Multi-robot exploration mission planning and stochastic increment replanning for load balance

Cai

2010

Front. Electr. Electron. Eng. China

View full text Add to dashboard Cite

Multi-robot mission planning is composed of assignment allocation and mobile-robot route planning in this paper. Multi-robot exploration missions adopts fuzzy c-mean (FCM) algorithm to allocate, and then, heterogeneous interactive cultural hybrid algorithm (HICHA) is devised for route planning in order to optimize mobilerobot execution path. Meanwhile, we design multi-robot mission replanning mechanism based on the rules system of greedy algorithm for dynamic stochastic increment missions. Finally, extensive simulation experiments were shown that FCM for assignment allocation and HICHA for route planning were efficacious for mobile-robot exploration mission planning. Furthermore, the improved greedy algorithm based on experience rules met dynamic stochastic increment missions replanning requirement for load balance.

show abstract

Genetics-Based Machine Learning Approach for Rule Acquisition in an AGV Transportation System

Cited by 7 publications

References 6 publications

Using simulation as an adaptive source of knowledge for the control of material handling systems

Using simulation as an adaptive source of knowledge for the control of material handling systems

Simulation aided, self-adapting knowledge based control of material handling systems

Multi-robot exploration mission planning and stochastic increment replanning for load balance

Contact Info

Product

Resources

About