This is not the latest version of this item. The latest version can be found here.
Learning constraint-based planning models from demonstrations
Name
Learning_Constraint_based_Planning_Models_From_Demonstrations.pdf
Description
Accepted version
Size
1.74 MB
Format
Adobe PDF
Checksum (MD5)
db7c94c405c1e22e62fdf564f4443339
Author(s)
Loula, Joao
Allen, Kelsey
Silver, Tom
Tenenbaum, Josh
Date Issued
2020
Journal
IEEE International Conference on Intelligent Robots and Systems
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Loula, Joao, Allen, Kelsey, Silver, Tom and Tenenbaum, Josh. 2020. "Learning constraint-based planning models from demonstrations." IEEE International Conference on Intelligent Robots and Systems.
Version
Author's final manuscript
Abstract
© 2020 IEEE. How can we learn representations for planning that are both efficient and flexible? Task and motion planning models are a good candidate, having been very successful in long-horizon planning tasks - however, they've proved challenging for learning, relying mostly on hand-coded representations. We present a framework for learning constraint-based task and motion planning models using gradient descent. Our model observes expert demonstrations of a task and decomposes them into modes - segments which specify a set of constraints on a trajectory optimization problem. We show that our model learns these modes from few demonstrations, that modes can be used to plan flexibly in different environments and to achieve different types of goals, and that the model can recombine these modes in novel ways.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1109/IROS45743.2020.9341535
