Skip to Main content Skip to Navigation

Intrinsic motivation mecanisms for incremental learning of visual saliency

Abstract : Conceiving autonomous perceptual systems, such as robots able to accomplish a set of tasks in a safe way, without any human assistance, is one of the biggest challenge of the century. To this end, the developmental robotics suggests to conceive robots able to learn by interacting directly with their environment, just like children would. This thesis is exploring such possibility while restricting the problem to the one of localizing objects of interest (or salient objects) within the robot’s environment.For that, we present in this work a mechanism able to learn visual saliency directly on a robot, then to use the learned model so as to localize salient objects within their environment. The advantage of this method is the creation of models dedicated to the robot’s environment and tasks it should be asked to accomplish, while remaining flexible to any change or novelty in the environment.Furthermore, we have developed exploration strategies based on intrinsic motivations, widely used in developmental robotics, to enable efficient learning of good quality. In particular, we adapted the IAC algorithm to visual saliency leanring, and proposed an extension, RL-IAC to allow an efficient exploration on mobile robots.In order to verify and analyze the performance of our algorithms, we have carried out various experiments on several robotics platforms, including a foveated system and a mobile robot, as well as publicly available datasets.
Complete list of metadata

Cited literature [301 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Thursday, August 10, 2017 - 5:15:07 PM
Last modification on : Wednesday, May 11, 2022 - 3:20:03 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01573851, version 1


Céline Craye. Intrinsic motivation mecanisms for incremental learning of visual saliency. Artificial Intelligence [cs.AI]. Université Paris Saclay (COmUE), 2017. English. ⟨NNT : 2017SACLY006⟩. ⟨tel-01573851⟩



Record views


Files downloads