Introspective Perception for Mobile Robots

TL;DR

This paper introduces introspective perception, a novel method enabling mobile robots to accurately predict their perception uncertainty by leveraging data redundancy and consistency, thereby improving autonomous navigation in challenging environments.

Contribution

The paper presents a new approach for learning empirical uncertainty models in perception algorithms without relying on idealized assumptions, applicable to real-world robotic tasks.

Findings

Accurately predicts uncertainty in stereo depth estimation.

Reduces localization errors in visual SLAM.

Demonstrates effectiveness on real robot data.

Abstract

Perception algorithms that provide estimates of their uncertainty are crucial to the development of autonomous robots that can operate in challenging and uncontrolled environments. Such perception algorithms provide the means for having risk-aware robots that reason about the probability of successfully completing a task when planning. There exist perception algorithms that come with models of their uncertainty; however, these models are often developed with assumptions, such as perfect data associations, that do not hold in the real world. Hence the resultant estimated uncertainty is a weak lower bound. To tackle this problem we present introspective perception - a novel approach for predicting accurate estimates of the uncertainty of perception algorithms deployed on mobile robots. By exploiting sensing redundancy and consistency constraints naturally present in the data collected by a mobile robot, introspective perception learns an empirical model of the error distribution of perception algorithms in the deployment environment and in an autonomously supervised manner. In this paper, we present the general theory of introspective perception and demonstrate successful implementations for two different perception tasks. We provide empirical results on challenging real-robot data for introspective stereo depth estimation and introspective visual simultaneous localization and mapping and show that they learn to predict their uncertainty with high accuracy and leverage this information to significantly reduce state estimation errors for an autonomous mobile robot.