Vecerik, M;
Regli, JB;
Sushkov, O;
Barker, D;
Pevceviciute, R;
Rothörl, T;
Schuster, C;
... Scholz, J; + view all
(2020)
S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency.
In: Kober, J and Ramos, F and Tomlin, C, (eds.)
Proceedings of the 2020 Conference on Robot Learning.
(pp. pp. 449-460).
Proceedings of Machine Learning Research (PMLR): Cambridge, MA, USA.
Preview |
Text
De Agapito Vicente_vecerik21a.pdf Download (6MB) | Preview |
Abstract
A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or usefulness for control, or else make use of large datasets annotated with specific features (bounding boxes, segmentations, etc.). However, both approaches often struggle to capture the fine-detail required for precision tasks on specific objects, e.g. grasping and mating a plug and socket. We argue that these difficulties arise from a lack of geometric structure in these models. In this work we advocate semantic 3D keypoints as a visual representation, and present a self-supervised training objective that can allow instance or category-level keypoints to be trained to 1-5 millimeter-accuracy with minimal supervision. Furthermore, unlike local texture-based approaches, our model integrates contextual information from a large area and is therefore robust to occlusion, noise, and lack of discernible texture. We demonstrate that this ability to locate semantic keypoints enables high level scripting of human understandable behaviours. Finally we show that these keypoints provide a good way to define reward functions for reinforcement learning and are a good representation for training agents.
| Type: | Proceedings paper |
|---|---|
| Title: | S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency |
| Event: | 2020 Conference on Robot Learning |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v155/vecerik21a.html |
| Language: | English |
| Additional information: | This is an Open Access paper published under a Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). |
| Keywords: | Semantic keypoints, self-supervised learning, robot manipulation |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10184269 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
