Team RoboSimian: Semi-autonomous Mobile Manipulation at the 2015 DARPA Robotics Challenge Finals
Creators
- Karumanchi, Sisir1
- Edelberg, Kyle1
- Baldwin, Ian1
- Nash, Jeremy1
- Satzinger, Brian2
- Reid, Jason1
- Bergh, Charles1
- Lau, Chelsea2
- Leichty, John1
-
Carpenter, Kalind1
- Shekels, Matthew1
- Gildner, Matthew1
- Newill-Smith, David1
- Carlton, Jason1
- Koehler, John1
-
Dobreva, Tatyana1
- Frost, Matthew1
- Hebert, Paul1
- Borders, James1
- Ma, Jeremy1
- Douillard, Bertrand1
- Shankar, Krishna3
- Byl, Katie2
- Burdick, Joel3
- Backes, Paul1
- Kennedy, Brett1
Contributors
Abstract
This article discusses hardware and software improvements to the RoboSimian system leading up to and during the 2015 DARPA Robotics Challenge (DRC) Finals. Team RoboSimian achieved a 5th place finish by achieving 7 points in 47:59 min. We present an architecture that was structured to be adaptable at the lowest level and repeatable at the highest level. The low-level adaptability was achieved by leveraging tactile measurements from force torque sensors in the wrist coupled with whole body motion primitives. We use the term "behaviors" to conceptualize this low-level adaptability. Each behavior is a contact-triggered state machine that enables execution of short order manipulation and mobility tasks autonomously. At a high level, we focused on a teach-and-repeat style of development by storing executed behaviors and navigation poses in object/task frame for recall later. This enabled us to perform tasks with high repeatability on competition day while being robust to task differences from practice to execution.
Additional Information
© 2018 Springer International Publishing AG, part of Springer Nature. First Online: 10 April 2018. The research described in this publication was carried out at the Jet Propulsion Laboratory, California Institute of Technology, with funding from the DARPA Robotics Challenge Track A program through an agreement with NASA with contributions from the Army Research Lab's RCTA program.Additional details
Identifiers
- Eprint ID
- 86288
- DOI
- 10.1007/978-3-319-74666-1_6
- Resolver ID
- CaltechAUTHORS:20180508-141832802
Related works
- Describes
- 10.1007/978-3-319-74666-1_6 (DOI)
- http://resolver.caltech.edu/CaltechAUTHORS:20170404-102045441 (URL)
Funding
- Caltech/JPL
- Defense Advanced Research Projects Agency (DARPA)
Dates
- Created
-
2018-05-08Created from EPrint's datestamp field
- Updated
-
2021-11-15Created from EPrint's last_modified field
Caltech Custom Metadata
- Series Name
- Springer Tracts in Advanced Robotics
- Series Volume or Issue Number
- 121