A perception pipeline for expeditionary autonomous ground vehicles

Josh Zapf; Gaurav Ahuja; Jeremie Papon; Daren Lee; Jeremy Nash; Arturo Rankin

doi:10.1117/12.2266690

Translator Disclaimer

5 May 2017 A perception pipeline for expeditionary autonomous ground vehicles

Josh Zapf, Gaurav Ahuja, Jeremie Papon, Daren Lee, Jeremy Nash, Arturo Rankin

Author Affiliations +

Proceedings Volume 10195, Unmanned Systems Technology XIX; 101950F (2017) https://doi.org/10.1117/12.2266690
Event: SPIE Defense + Security, 2017, Anaheim, California, United States

Abstract

Expeditionary environments create special challenges for perception systems in autonomous ground vehicles. To address these challenges, a perception pipeline has been developed that fuses data from multiple sensors (color, thermal, LIDAR) with different sensing modalities and spatial resolutions. The paper begins with in-depth discussion of the multi-sensor calibration procedure. It then follows the flow of data through the perception pipeline, detailing the process by which the sensor data is combined in the world model representation. Topics of interest include stereo filtering, stereo and LIDAR ground segmentation, pixel classification, 3D occupancy grid aggregation, and costmap generation

Conference Presentation

Citation Download Citation

Josh Zapf, Gaurav Ahuja, Jeremie Papon, Daren Lee, Jeremy Nash, and Arturo Rankin "A perception pipeline for expeditionary autonomous ground vehicles", Proc. SPIE 10195, Unmanned Systems Technology XIX, 101950F (5 May 2017); https://doi.org/10.1117/12.2266690

ACCESS THE FULL ARTICLE