RL-IAC: An Exploration Policy for Online Saliency Learning on an Autonomous Mobile Robot

Céline Craye 1, 2, 3 David Filliat 1, 2 Jean-François Goudou 3
2 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : In the context of visual object search and localization, saliency maps provide an efficient way to find object candidates in images. Unlike most approaches, we propose a way to learn saliency maps directly on a robot, by exploring the environment, discovering salient objects using geometric cues, and learning their visual aspects. More importantly, we provide an autonomous exploration strategy able to drive the robot for the task of learning saliency. For that, we describe the Reinforcement Learning-Intelligent Adaptive Curiosity algorithm (RL-IAC), a mechanism based on IAC (Intelligent Adaptive Curiosity) able to guide the robot through areas of the space where learning progress is high, while minimizing the time spent to move in its environment without learning. We demonstrate first that our saliency approach is an efficient tool to generate relevant object boxes proposal in the input image and significantly outperforms state-of-the-art algorithms. Second, we show that RL-IAC can drastically decrease the required time for learning saliency compared to random exploration.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01392947
Contributor : Céline Craye <>
Submitted on : Wednesday, November 16, 2016 - 9:03:07 AM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Thursday, March 16, 2017 - 2:02:13 PM

File

root.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01392947, version 2

Citation

Céline Craye, David Filliat, Jean-François Goudou. RL-IAC: An Exploration Policy for Online Saliency Learning on an Autonomous Mobile Robot. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct 2016, Daejeon, South Korea. ⟨hal-01392947v2⟩

Share

Metrics

Record views

377

Files downloads

370