Home/Introspective Perception: Learning to Predict Failures in Vision Systems

Introspective Perception: Learning to Predict Failures in Vision Systems

Shreyansh Daftry, Sam Zeng, J. Andrew (Drew) Bagnell and Martial Hebert
Conference Paper, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016), July, 2016

Download Publication (PDF)

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

As robots aspire for long-term autonomous operations in complex dynamic environments, the ability to reliably take mission-critical decisions in ambiguous situations becomes critical. This motivates the need to build systems that have situational awareness to assess how qualified they are at that moment to make a decision. We call this self-evaluating capability as introspection. In this paper, we take a small step in this direction and propose a generic framework for introspective behavior in perception systems. Our goal is to learn a model to reliably predict failures in a given system, with respect to a task, directly from input sensor data. We present this in the context of vision-based autonomous MAV flight in outdoor natural environments, and show that it effectively handles uncertain situations.

BibTeX Reference
@conference{Daftry-2016-5565,
title = {Introspective Perception: Learning to Predict Failures in Vision Systems},
author = {Shreyansh Daftry and Sam Zeng and J. Andrew (Drew) Bagnell and Martial Hebert},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016)},
sponsor = {ONR through "Provably-Stable Vision-Based Control of High-Speed Flight through Forests and Urban Environments" MURI},
publisher = {IEEE},
month = {July},
year = {2016},
}
2017-09-13T10:38:20+00:00