Estimating Motion Codes from Demonstration Videos
arXiv:2007.15841 · doi:10.1109/IROS45743.2020.9341065
Abstract
A motion taxonomy can encode manipulations as a binary-encoded representation, which we refer to as motion codes. These motion codes innately represent a manipulation action in an embedded space that describes the motion's mechanical features, including contact and trajectory type. The key advantage of using motion codes for embedding is that motions can be more appropriately defined with robotic-relevant features, and their distances can be more reasonably measured using these motion features. In this paper, we develop a deep learning pipeline to extract motion codes from demonstration videos in an unsupervised manner so that knowledge from these videos can be properly represented and used for robots. Our evaluations show that motion codes can be extracted from demonstrations of action in the EPIC-KITCHENS dataset.
arXiv commentIROS 2020 Submission -- 6 pages; initial upload (Last updated July 31st 2020)
References in corpus (7)
- Distributed Representations of Words and Phrases and their Compositionality
- Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
- A Survey of Knowledge Representation in Service Robotics
- Functional Object-Oriented Network for Manipulation Learning
- Functional Object-Oriented Network: Construction & Expansion
- Manipulation Motion Taxonomy and Coding for Robots
- A Motion Taxonomy for Manipulation Embedding