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.
@article{arxiv.1607.08665,
title = {Introspective Perception: Learning to Predict Failures in Vision Systems},
author = {Shreyansh Daftry and Sam Zeng and J. Andrew Bagnell and Martial Hebert},
journal= {arXiv preprint arXiv:1607.08665},
year = {2016}
}
Comments
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016)