A Caltech Library Service

Fault detection and isolation from uninterpreted data in robotic sensorimotor cascades

Censi, Andrea and Håkansson, Magnus and Murray, Richard M. (2012) Fault detection and isolation from uninterpreted data in robotic sensorimotor cascades. In: 2012 IEEE International Conference on Robotics and Automation (ICRA). IEEE , Piscataway, NJ, pp. 229-236. ISBN 978-1-4673-1403-9.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


One of the challenges in designing the next generation of robots operating in non-engineered environments is that there seems to be an infinite amount of causes that make the sensor data unreliable or actuators ineffective. In this paper, we discuss what faults are possible to detect using zero modeling effort: we start from uninterpreted streams of observations and commands, and without a prior knowledge of a model of the world. We show that in sensorimotor cascades it is possible to define static faults independently of a nominal model. We define an information-theoretic usefulness of a sensor reading and we show that it captures several kind of sensorimotor faults frequently encountered in practice. We particularize these ideas to models proposed in previous work as suitable candidates for describing generic sensorimotor cascades. We show several examples with camera and range-finder data, and we discuss a possible way to integrate these techniques in an existing robot software architecture.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Censi, Andrea0000-0001-5162-0398
Murray, Richard M.0000-0002-5785-7481
Additional Information:© 2012 IEEE. Date of Current Version: 28 June 2012. We are grateful to Larry Matthies, Thomas Werne, and Marco Pavone at JPL for lending the Landroid platform and assisting with the software development. Part of this research has been supported by the DARPA MSEE program.
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA) MSEE ProgramUNSPECIFIED
Record Number:CaltechAUTHORS:20120703-105934140
Persistent URL:
Official Citation:Censi, Andrea; Hakansson, Magnus; Murray, Richard M.; , "Fault detection and isolation from uninterpreted data in robotic sensorimotor cascades," Robotics and Automation (ICRA), 2012 IEEE International Conference on , vol., no., pp.229-236, 14-18 May 2012 doi: 10.1109/ICRA.2012.6225311 URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:32252
Deposited By: Tony Diaz
Deposited On:06 Jul 2012 20:53
Last Modified:09 Nov 2021 21:26

Repository Staff Only: item control page