View Full Document

Real-Time Acquisition of Compact



View the full content.
View Full Document
View Full Document

2 views

Unformatted text preview:

Real Time Acquisition of Compact Volumetric Maps with Mobile Robots Christian Martin and Sebastian Thrun School of Computer Science Carnegie Mellon University Pittsburgh PA 15213 Abstract This paper describes an online algorithm for generating compact 3D maps of mobile robot environments Maps generated by our approach consist of small numbers of planar surfaces which are augmented by fine grained polygons for non flat environmental features Our approach builds on the expectation maximization EM algorithm but develops a new incremental version that can be executed in real time Experimental results obtained in corridor type environments illustrate that compact and accurate maps can be acquired in real time from range and camera data collected by a mobile robot 1 Introduction This paper presents an algorithm for generating compact models of indoor environments in real time from range and camera measurements The vast majority of successful robot mapping algorithms represent maps by grids 4 raw point measurements 5 7 or line segments 1 While such representations appear to be sufficient for navigation they suffer from two major disadvantages First there are intrinsic scaling limitations For example while two dimensional occupancy maps require relatively little memory the memory requirements of the same approach in 3D are prohibitive despite recent work on this topic 9 Second and more importantly such maps fail to capture the true nature of indoor environments Indoor environments are often composed of walls furniture doors windows etc many of which are characterized by specific geometric features e g are flat An understanding of such objects and their geometric properties e g flatness will inevitably lead to new more powerful mapping algorithms that can generate more accurate maps This paper provides a step in the direction of building more compact maps using a simple object representation We describe an algorithm that identifies flat rectangular surfaces form the sensor



Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view Real-Time Acquisition of Compact and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Real-Time Acquisition of Compact and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?