Downloads & Free Reading Options - Results

Life detection based on a single type of information sources detection technology cannot completely meet the needs of the earthquake relief. First, we analyze the present situation of typical life detection technology, then the advantages of multi-sensor synergy detection technique are given. Second, we explained the platform structure and information fusion model. Finally, the fusion rule based on Dezert-Smarandache theory (DSmT) is used to achieve the decision level fusion. We present the results reached by the fusion with the conjunctive rule, the Dempster, the Yager and the DSmT. The experiments show that DSmT can get more comprehensive and more accurate information about the scene of rescue and survivors. The multi-sensor synergy life detection platform based on DSmT is more suitable for complex quake rescue environment

Robust environment perception is essential for decision-making on robots operating in complex domains. Intelligent task execution requires principled treatment of uncertainty sources in a robot's observation model. This is important not only for low-level observations (e.g., accelerometer data), but also for high-level observations such as semantic object labels. This paper formalizes the concept of macro-observations in Decentralized Partially Observable Semi-Markov Decision Processes (Dec-POSMDPs), allowing scalable semantic-level multi-robot decision making. A hierarchical Bayesian approach is used to model noise statistics of low-level classifier outputs, while simultaneously allowing sharing of domain noise characteristics between classes. Classification accuracy of the proposed macro-observation scheme, called Hierarchical Bayesian Noise Inference (HBNI), is shown to exceed existing methods. The macro-observation scheme is then integrated into a Dec-POSMDP planner, with hardware experiments running onboard a team of dynamic quadrotors in a challenging domain where noise-agnostic filtering fails. To the best of our knowledge, this is the first demonstration of a real-time, convolutional neural net-based classification framework running fully onboard a team of quadrotors in a multi-robot decision-making domain.

Decision making is related to the context of a submarine approach officer's (AO) task during an encounter with a sonar contact. A typology of decisions is developed and a single type, the doubly uncertain decision class, selected as most relevant to the context. Theories of decision making are then reviewed and related to the various decision types. Finally, a single model of decision making is selected, and a modified version of that model is expanded for application to the approach officer task. Areas of research needed to verify this application and fill-in details of its functioning are suggested, especially with respect to levels of expertise differences.

Life detection based on a single type of information sources detection technology cannot completely meet the needs of the earthquake relief. First, we analyze the present situation of typical life detection technology, then the advantages of multi-sensor synergy detection technique are given. Second, we explained the platform structure and information fusion model.

This paper presents a literature review on the theory, applications and software of Bi-level, Multi –Level Multiple Criteria Decision Making and TOPSIS (Technique for Order Preference by Similarity Ideal Solution) Approach.

Top-level acquisition decisions are complex and multi-objective. This implies difficulties in appropriately accounting for all relevant factors to select the best alternative. In addition, there are difficulties and deficiencies in the actual implementation of the decision process. The difficulties and deficiencies in the top-level acquisition decision-making are explored by this thesis. The thesis suggests improvements through intensive use of quantitative, judgment-based decision technique derived from Multi-Attribute Utility Theory (MAUT). Emphasis is put on demonstrating MAUT's capability for incorporating subjective judgment, in order to reduce the existing doubts about its usefulness for top-level decision-making. The thesis recommends use of the MAUT procedure as the central tool for comprehensive evaluation of the decision alternatives. It argues that such use would solve some of the essential decision-making problems and in addition contribute to the quality and efficiency of the decision process.

Life detection based on a single type of information sources detection technology cannot completely meet the needs of the earthquake relief. First, we analyze the present situation of typical life detection technology, then the advantages of multi-sensor synergy detection technique are given.

Life detection based on a single type of information sources detection technology cannot completely meet the needs of the earthquake relief. First, we analyze the present situation of typical life detection technology, then the advantages of multi-sensor synergy detection technique are given.