Introspective perception: Learning to predict failures in vision systems
Authors:
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1743-1750
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.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Discovering joint audio–visual codewords for video event detectionMachine Vision and Applications, 2013
- Development of advanced FDD and FTC techniques with application to an unmanned quadrotor helicopter testbedJournal of the Franklin Institute, 2013
- Flexible and User-Centric Camera Calibration using Planar Fiducial Markers2013
- Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators2012
- Knows what it knows: a framework for self-aware learningMachine Learning, 2010
- Gaussian Processes for Object CategorizationInternational Journal of Computer Vision, 2009
- Toward Reliable Off Road Autonomous Vehicles Operating in Challenging EnvironmentsThe International Journal of Robotics Research, 2006
- Generating Estimates of Classification Confidence for a Case-Based Spam FilterLecture Notes in Computer Science, 2005
- Classifier conditional posterior probabilities1998