scholarly journals A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems

2016 ◽  
Vol 2016 ◽  
pp. 1-15 ◽  
Author(s):  
Shiguang Yue ◽  
Kristina Yordanova ◽  
Frank Krüger ◽  
Thomas Kirste ◽  
Yabing Zha
Keyword(s):  
Domain Knowledge ◽  
Decision Model ◽  
Training Dataset ◽  
Predator Prey ◽  
Modeling Methods ◽  
Model Free ◽  
Goal Recognition ◽  
Cooperative Behaviors ◽  
Partially Observable ◽  
Simulation Systems

Multiagent goal recognition is important in many simulation systems. Many of the existing modeling methods need detailed domain knowledge of agents’ cooperative behaviors and a training dataset to estimate policies. To solve these problems, we propose a novel decentralized partially observable decision model (Dec-POMDM), which models cooperative behaviors by joint policies. In this compact way, we only focus on the distribution of joint policies. Additionally, a model-free algorithm, cooperative colearning based on Sarsa, is exploited to estimate agents’ policies under the assumption of rationality, which makes the training dataset unnecessary. In the inference, considering that the Dec-POMDM is discrete and its state space is large, we implement a marginal filter (MF) under the framework of the Dec-POMDM, where the initial world states and results of actions are uncertain. In the experiments, a new scenario is designed based on the standard predator-prey problem: we increase the number of preys, and our aim is to recognize the real target of predators. Experiment results show that (a) our method recognizes goals well even when they change dynamically; (b) the Dec-POMDM outperforms supervised trained HMMs in terms of precision, recall, and F-measure; and (c) the MF infers goals more efficiently than the particle filter under the framework of the Dec-POMDM.

scholarly journals A Decentralized Partially Observable Markov Decision Model with Action Duration for Goal Recognition in Real Time Strategy Games

2017 ◽  
Vol 2017 ◽  
pp. 1-15 ◽  
Author(s):  
Peng Jiao ◽  
Kai Xu ◽  
Shiguang Yue ◽  
Xiangyu Wei ◽  
Lin Sun
Keyword(s):  
Real Time ◽  
Domain Knowledge ◽  
Dynamic Bayesian Network ◽  
Training Dataset ◽  
Time Duration ◽  
Model Free ◽  
Strategy Games ◽  
Markov Decision Model ◽  
Goal Recognition ◽  
Group B

Multiagent goal recognition is a tough yet important problem in many real time strategy games or simulation systems. Traditional modeling methods either are in great demand of detailed agents’ domain knowledge and training dataset for policy estimation or lack clear definition of action duration. To solve the above problems, we propose a novel Dec-POMDM-T model, combining the classic Dec-POMDP, an observation model for recognizer, joint goal with its termination indicator, and time duration variables for actions with action termination variables. In this paper, a model-free algorithm named cooperative colearning based on Sarsa is used. Considering that Dec-POMDM-T usually encounters multiagent goal recognition problems with different sorts of noises, partially missing data, and unknown action durations, the paper exploits the SIS PF with resampling for inference under the dynamic Bayesian network structure of Dec-POMDM-T. In experiments, a modified predator-prey scenario is adopted to study multiagent joint goal recognition problem, which is the recognition of the joint target shared among cooperative predators. Experiment results show that (a) Dec-POMDM-T works effectively in multiagent goal recognition and adapts well to dynamic changing goals within agent group; (b) Dec-POMDM-T outperforms traditional Dec-MDP-based methods in terms of precision, recall, andF-measure.

scholarly journals Simultaneous-Fault Diagnosis of Automotive Engine Ignition Systems Using Prior Domain Knowledge and Relevance Vector Machine

2013 ◽  
Vol 2013 ◽  
pp. 1-19 ◽  
Author(s):  
Chi-Man Vong ◽  
Pak-Kin Wong ◽  
Weng-Fai Ip ◽  
Chi-Chong Chiu
Keyword(s):  
Fault Diagnosis ◽  
Domain Knowledge ◽  
Diagnostic System ◽  
Relevance Vector Machine ◽  
Training Dataset ◽  
Decision Threshold ◽  
Single Fault ◽  
Automotive Engine ◽  
Probabilistic Classification ◽  
Threshold Optimization

Engine ignition patterns can be analyzed to identify the engine fault according to both the specific prior domain knowledge and the shape features of the patterns. One of the challenges in ignition system diagnosis is that more than one fault may appear at a time. This kind of problem refers to simultaneous-fault diagnosis. Another challenge is the acquisition of a large amount of costly simultaneous-fault ignition patterns for constructing the diagnostic system because the number of the training patterns depends on the combination of different single faults. The above problems could be resolved by the proposed framework combining feature extraction, probabilistic classification, and decision threshold optimization. With the proposed framework, the features of the single faults in a simultaneous-fault pattern are extracted and then detected using a new probabilistic classifier, namely, pairwise coupling relevance vector machine, which is trained with single-fault patterns only. Therefore, the training dataset of simultaneous-fault patterns is not necessary. Experimental results show that the proposed framework performs well for both single-fault and simultaneous-fault diagnoses and is superior to the existing approach.

Research on Ontology Modeling Method of Smart Grid

2013 ◽  
Vol 291-294 ◽  
pp. 2079-2083
Author(s):  
Hong Peng He ◽  
Yan Hao Huang ◽  
Jun Liu ◽  
Jian Lei Fan
Keyword(s):  
Smart Grid ◽  
Domain Knowledge ◽  
Power Grid ◽  
Modeling Method ◽  
Continuous Development ◽  
Modeling Methods ◽  
Ontology Modeling ◽  
Knowledge Ontology

Smart grid makes new request for the representation and application of power grid knowledge. To solve the problem of “information isolated island” caused by the continuous development of power grid and the ineffectively use of massive domain knowledge, ontology technology is introduced into the smart grid field. Each link of smart grid is analyzed and new request for knowledge it makes is introduced. Then a simple introduction of ontology and ontology modeling is made. Referring to the defects of existing ontology modeling methods and considering the specific reality of smart grid, an ontology modeling method suitable for the smart grid field is presented, which is aiming at providing guidance on ontology modeling of smart grid. Finally a modeling example is given which proves the feasibility and efficiency of the method.

Enabling Efficient Model-Free Control of Large-Scale Canals by Exploiting Domain Knowledge

2020 ◽  
pp. 1-1
Author(s):  
Tao Ren ◽  
Jianwei Niu ◽  
Lei Shu ◽  
Gerhard P. Hancke ◽  
Jiyan Wu ◽  
...  
Keyword(s):  
Domain Knowledge ◽  
Large Scale ◽  
Model Free ◽  
Model Free Control

Domain Knowledge Assisted Training Dataset Generation for Metasurface Designs

2021 ◽  
Author(s):  
Zhaohui We ◽  
Zhao Zhou ◽  
Yufeng Zhang ◽  
Puchu Li ◽  
Jian Ren ◽  
...  
Keyword(s):  
Domain Knowledge ◽  
Training Dataset

scholarly journals A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos

2021 ◽  
pp. 147592172110104
Author(s):  
Muhammad Monjurul Karim ◽  
Ruwen Qin ◽  
Genda Chen ◽  
Zhaozheng Yin
Keyword(s):  
Neural Network ◽  
Domain Knowledge ◽  
Video Data ◽  
Training Dataset ◽  
Training Method ◽  
Structural Elements ◽  
Bridge Inspection ◽  
The Neural Network ◽  
Intelligence Models ◽  
National Bridge Inventory

Bridge inspection is an important step in preserving and rehabilitating transportation infrastructure for extending their service lives. The advancement of mobile robotic technology allows the rapid collection of a large amount of inspection video data. However, the data are mainly the images of complex scenes, wherein a bridge of various structural elements mix with a cluttered background. Assisting bridge inspectors in extracting structural elements of bridges from the big complex video data, and sorting them out by classes, will prepare inspectors for the element-wise inspection to determine the condition of bridges. This article is motivated to develop an assistive intelligence model for segmenting multiclass bridge elements from the inspection videos captured by an aerial inspection platform. With a small initial training dataset labeled by inspectors, a Mask Region-based Convolutional Neural Network pre-trained on a large public dataset was transferred to the new task of multiclass bridge element segmentation. Besides, the temporal coherence analysis attempts to recover false negatives and identify the weakness that the neural network can learn to improve. Furthermore, a semi-supervised self-training method was developed to engage experienced inspectors in refining the network iteratively. Quantitative and qualitative results from evaluating the developed deep neural network demonstrate that the proposed method can utilize a small amount of time and guidance from experienced inspectors (3.58 h for labeling 66 images) to build the network of excellent performance (91.8% precision, 93.6% recall, and 92.7% f1-score). Importantly, the article illustrates an approach to leveraging the domain knowledge and experiences of bridge professionals into computational intelligence models to efficiently adapt the models to varied bridges in the National Bridge Inventory.

scholarly journals Adaptive Thompson Sampling Stacks for Memory Bounded Open-Loop Planning

2019 ◽  
Author(s):  
Thomy Phan ◽  
Thomas Gabor ◽  
Robert Müller ◽  
Christoph Roch ◽  
Claudia Linnhoff-Popien
Keyword(s):  
Domain Knowledge ◽  
Planning Horizon ◽  
Open Loop ◽  
Generative Model ◽  
Benchmark Problems ◽  
Adaptive Memory ◽  
Memory Consumption ◽  
Thompson Sampling ◽  
Planning Algorithms ◽  
Partially Observable

We propose Stable Yet Memory Bounded Open-Loop (SYMBOL) planning, a general memory bounded approach to partially observable open-loop planning. SYMBOL maintains an adaptive stack of Thompson Sampling bandits, whose size is bounded by the planning horizon and can be automatically adapted according to the underlying domain without any prior domain knowledge beyond a generative model. We empirically test SYMBOL in four large POMDP benchmark problems to demonstrate its effectiveness and robustness w.r.t. the choice of hyperparameters and evaluate its adaptive memory consumption. We also compare its performance with other open-loop planning algorithms and POMCP.

Sign in / Sign up

Export Citation Format

Share Document