JPL Technical Report Server

Machine Vision based Sample-Tube Localization for Mars Sample Return

Show simple item record Daftry, Shreyansh Ridge, B. Seto, W. Pham, T. Illhardt, P. Maggiolino, G. Van der Merwe, M. Brinkman, A. Mayo, J. Kulczyski, E. Detry, R. 2022-03-01T00:44:26Z 2022-03-01T00:44:26Z 2021-03-06
dc.identifier.citation 2021 IEEE Aerospace Conference, Big Sky, Montana, March 6-13, 2021
dc.identifier.clearanceno CL#21-0137
dc.description.abstract A potential Mars Sample Return (MSR) architecture is being jointly studied by NASA and ESA. As currently envisioned, the MSR campaign consists of a series of 3 missions: sample cache, fetch and return to Earth. In this paper, we focus on the fetch part of the MSR, and more specifically the problem of autonomously detecting and localizing sample tubes deposited on the Martian surface. Towards this end, we study two machine-vision based approaches: First, a geometrydriven approach based on template matching that uses hardcoded filters and a 3D shape model of the tube; and second, a data-driven approach based on convolutional neural networks (CNNs) and learned features. Furthermore, we present a large benchmark dataset of sample-tube images, collected in representative outdoor environments and annotated with ground truth segmentation masks and locations. The dataset was acquired systematically across different terrain, illumination conditions and dust-coverage; and benchmarking was performed to study the feasibility of each approach, their relative strengths and weaknesses, and robustness in the presence of adverse environmental conditions.
dc.description.sponsorship NASA/JPL en_US
dc.language.iso en_US
dc.publisher Pasadena, CA: Jet Propulsion Laboratory, National Aeronautics and Space Administration, 2021
dc.title Machine Vision based Sample-Tube Localization for Mars Sample Return
dc.type Preprint

Files in this item

This item appears in the following Collection(s)

Show simple item record



My Account