Zobrazit v EDS

Dynamic Anchoring Agent: A Probabilistic Object Anchoring Framework for Semantic World Modeling

Uloženo v:
Podrobná bibliografie
Název: Dynamic Anchoring Agent: A Probabilistic Object Anchoring Framework for Semantic World Modeling
Autoři: Zongyao Yi, Martin Günther, Joachim Hertzberg
Zdroj: Proceedings of the International Florida Artificial Intelligence Research Society Conference, Vol 37 (2024)
Informace o vydavateli: University of Florida George A Smathers Libraries, 2024.
Rok vydání: 2024
Témata: Technology, semantic world modeling, Electronic computers. Computer science, probabilistic anchoring, QA75.5-76.95, multiple object tracking
Popis: Semantic world modeling has been studied extensively, with the goal of enabling robots to understand and interact with their environment. However, existing approaches to semantic world modeling rely on well-defined perceptual data, such as distinct visual features. In situations where different objects are difficult to distinguish based on perceptual data alone, the resulting world model will be ambiguous and inconsistent. To address this challenge, we present the Dynamic Anchoring Agent (DAA), a probabilistic object anchoring framework for semantic world modeling that uses domain knowledge and reasoning to handle the ambiguity of sensor data through probabilistic anchoring. It includes a Multiple Hypothesis Tracker (MHT) as a filter for noisy observations, and a knowledge base that encodes domain knowledge and scene context to reduce uncertainty in the anchoring process. The framework is evaluated on both synthetic and real-world datasets, demonstrating its effectiveness in resolving association ambiguities in the presence of identical-looking instances. It has also been integrated into a real robot platform. We show that with the help of domain knowledge and scene context, the proposed framework outperforms traditional pure data-based algorithms in terms of identification accuracy, and can effectively resolve ambiguities between sensor-identical object instances.
Druh dokumentu: Article
ISSN: 2334-0762
DOI: 10.32473/flairs.37.1.135576
Přístupová URL adresa: https://doaj.org/article/e82c937bc2ab4c1db697a360caf43892
Rights: CC BY NC
Přístupové číslo: edsair.doi.dedup.....69effa9d04b2c6968351fa977e9df8d5
Databáze: OpenAIRE
Popis
Abstrakt:Semantic world modeling has been studied extensively, with the goal of enabling robots to understand and interact with their environment. However, existing approaches to semantic world modeling rely on well-defined perceptual data, such as distinct visual features. In situations where different objects are difficult to distinguish based on perceptual data alone, the resulting world model will be ambiguous and inconsistent. To address this challenge, we present the Dynamic Anchoring Agent (DAA), a probabilistic object anchoring framework for semantic world modeling that uses domain knowledge and reasoning to handle the ambiguity of sensor data through probabilistic anchoring. It includes a Multiple Hypothesis Tracker (MHT) as a filter for noisy observations, and a knowledge base that encodes domain knowledge and scene context to reduce uncertainty in the anchoring process. The framework is evaluated on both synthetic and real-world datasets, demonstrating its effectiveness in resolving association ambiguities in the presence of identical-looking instances. It has also been integrated into a real robot platform. We show that with the help of domain knowledge and scene context, the proposed framework outperforms traditional pure data-based algorithms in terms of identification accuracy, and can effectively resolve ambiguities between sensor-identical object instances.
ISSN:23340762
DOI:10.32473/flairs.37.1.135576