Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published May 25, 2016 | Published
Book Section - Chapter Open

Stereo vision-based obstacle avoidance for micro air vehicles using an egocylindrical image space representation

Abstract

Micro air vehicles which operate autonomously at low altitude in cluttered environments require a method for onboard obstacle avoidance for safe operation. Previous methods deploy either purely reactive approaches, mapping low-level visual features directly to actuator inputs to maneuver the vehicle around the obstacle, or deliberative methods that use on-board 3-D sensors to create a 3-D, voxel-based world model, which is then used to generate collision free 3-D trajectories. In this paper, we use forward-looking stereo vision with a large horizontal and vertical field of view and project range from stereo into a novel robot-centered, cylindrical, inverse range map we call an egocylinder. With this implementation we reduce the complexity of our world representation from a 3D map to a 2.5D image-space representation, which supports very efficient motion planning and collision checking, and allows to implement configuration space expansion as an image processing function directly on the egocylinder. Deploying a fast reactive motion planner directly on the configuration space expanded egocylinder image, we demonstrate the effectiveness of this new approach experimentally in an indoor environment.

Additional Information

© 2016 Society of Photo-optical Instrumentation Engineers (SPIE). This work was funded by the Army Research Laboratory under the Micro Autonomous Systems & Technology Collaborative Technology Alliance program (MAST-CTA). JPL contributions were carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration.

Attached Files

Published - 98361R.pdf

Files

98361R.pdf
Files (972.9 kB)
Name Size Download all
md5:58ec43e444cec6bcd6114e555aff8f31
972.9 kB Preview Download

Additional details

Created:
August 20, 2023
Modified:
January 14, 2024