Sökning: id:"swepub:oai:DiVA.org:oru-112139" >
Planning for Learni...
Planning for Learning Object Properties
-
- Lamanna, Leonardo (författare)
- Fondazione Bruno Kessler, Trento, Italy; Department of Information Engineering, University of Brescia, Brescia, Italy
-
- Serafini, Luciano (författare)
- Fondazione Bruno Kessler, Trento, Italy
-
- Faridghasemnia, Mohamadreza, 1991- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Center for Applied Autonomous Sensor Systems (AASS)
-
visa fler...
-
- Saffiotti, Alessandro, Professor, 1960- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Center for Applied Autonomous Sensor Systems (AASS)
-
- Saetti, Alessandro (författare)
- Department of Information Engineering, University of Brescia, Brescia, Italy
-
- Gerevini, Alfonso (författare)
- Department of Information Engineering, University of Brescia, Brescia, Italy
-
- Traverso, Paolo (författare)
- Fondazione Bruno Kessler, Trento, Italy
-
visa färre...
-
(creator_code:org_t)
- AAAI Press, 2023
- 2023
- Engelska.
-
Ingår i: Proceedings of the AAAI Conference on Artificial Intelligence. - : AAAI Press. - 9781577358800 ; , s. 12005-12013
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Learning systems
- Supervised learning
- Labeled data
- Learn
- Learning objects
- Machine learning models
- Object property
- Physical environments
- Property
- Real-world
- Sensory data
- Supervised machine learning
- Autonomous agents
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas