Abstract
Abstract—Hybrid systems are a compact and natural mechanism with which to address problems in robotics. This work introduces an approach to learning hybrid systems from demonstrations,
with an emphasis on extracting models that are
explicitly veriable and easily interpreted by robot operators. We fit a sequence of controllers using sequential importance sampling under a generative switching proportional controller task model.
Here, we parameterise controllers using a proportional gain and a visually veriable joint angle goal. Inference under this model is challenging, but we address this by introducing an attribution prior extracted from a neural end-to-end visuomotor control model. Given the sequence of controllers comprising a task, we simplify the trace using grammar parsing strategies, taking advantage of the sequence compositionality, before grounding
the controllers by training perception networks to predict goals given images. Using this approach, we are successfully able to induce a program for a visuomotor reaching task involving loops and conditionals from a single demonstration and a neural end-to-end model. In addition, we are able to discover the program used for a tower building task. We argue that computer programlike control systems are more interpretable than alternative endto-
end learning approaches, and that hybrid systems inherently allow for better generalisation across task congurations.
with an emphasis on extracting models that are
explicitly veriable and easily interpreted by robot operators. We fit a sequence of controllers using sequential importance sampling under a generative switching proportional controller task model.
Here, we parameterise controllers using a proportional gain and a visually veriable joint angle goal. Inference under this model is challenging, but we address this by introducing an attribution prior extracted from a neural end-to-end visuomotor control model. Given the sequence of controllers comprising a task, we simplify the trace using grammar parsing strategies, taking advantage of the sequence compositionality, before grounding
the controllers by training perception networks to predict goals given images. Using this approach, we are successfully able to induce a program for a visuomotor reaching task involving loops and conditionals from a single demonstration and a neural end-to-end model. In addition, we are able to discover the program used for a tower building task. We argue that computer programlike control systems are more interpretable than alternative endto-
end learning approaches, and that hybrid systems inherently allow for better generalisation across task congurations.
Original language | English |
---|---|
Title of host publication | Proceedings of Robotics: Science and Systems 2019 |
Editors | Antonio Bicchi, Hadas Kress-Gazit , Seth Hutchinson |
Place of Publication | Freiburg im Breisgau Germany |
Publisher | Robotics: Science and Systems Foundation |
Number of pages | 10 |
Volume | XV |
ISBN (Electronic) | 9780992374754 |
DOIs | |
Publication status | Published - 2019 |
Externally published | Yes |
Event | Robotics: Science and Systems 2019 - Freiburg im Breisgau, Germany Duration: 22 Jun 2019 → 26 Jun 2019 http://rss2019.informatik.uni-freiburg.de (Website) http://www.roboticsproceedings.org (Proceedings) |
Conference
Conference | Robotics: Science and Systems 2019 |
---|---|
Country | Germany |
City | Freiburg im Breisgau |
Period | 22/06/19 → 26/06/19 |
Internet address |
|