Dynamics-Aware Metric Embedding: Metric Learning in a Latent Space for Visual Planning
- Authors
- Hong, Mineui; Lee, Kyungjae; Kang, Minjae.; Jung, Wonsuhk.; Oh, Songhwai.
- Issue Date
- Apr-2022
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Integrated planning and learning; Machine learning for robot control; Task planning
- Citation
- IEEE Robotics and Automation Letters, v.7, no.2, pp 3388 - 3395
- Pages
- 8
- Journal Title
- IEEE Robotics and Automation Letters
- Volume
- 7
- Number
- 2
- Start Page
- 3388
- End Page
- 3395
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59356
- DOI
- 10.1109/LRA.2022.3146917
- ISSN
- 2377-3766
- Abstract
- In this letter, we consider vision-based control tasks of which the desired goals are given as target images. The problems are often addressed by an autonomous agent which optimizes a trajectory to minimize a manually designed cost function. However, it is challenging to design a suitable cost function for each goal by hand, especially, when the current and the goal states of the system are only described by visual observations. In order to tackle this issue, we propose a method called dynamics-aware metric embedding (DAME), which generates cost functions in a self-supervised manner to help the agent plan the controls to accomplish the desired goals. The proposed method learns a metric function that reflects how easy to find a path connecting two states considering the dynamics of the system. To learn the metric between states, we utilize a measure named probabilistic reachability, which is computed using the probability of reaching from one state to the other state via random walk. We evaluate the proposed method in several vision-based control tasks, including both various simulation benchmarks and real-world table-top manipulation tasks, and observe that DAME outperforms other baseline algorithms by over 30% in the terms of success rate. © 2016 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > Department of Artificial Intelligence > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59356)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.