Precision Instrument Targeting via Image Registration for the Mars 2020 Rover
Authors: Gary Doran, David R. Thompson, Tara Estlin
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To evaluate the ability of our proposed precision targeting approach to identify targets in an RMI image and to characterize the factors that affect its performance, we used over 3,800 images acquired by the MSL rover during the first 1,200 sols of operation. To train the random forest classifier, we analyzed the roughly 16,500 alignments produced by our algorithm using 2,500 landmarks. Figure 5: Performance as a function of three factors: (left) the number of landmarks initially extracted from the images (and therefore the amount of information that must be uplinked to the spacecraft), (center) the amount of overlap between the Sol N and N + 1 images, and (right) the difference in illumination angle between the images. |
| Researcher Affiliation | Academia | Gary Doran, David R. Thompson, Tara Estlin Jet Propulsion Laboratory, California Institute of Technology {Gary.B.Doran.Jr,David.R.Thompson,Tara.A.Estlin}@jpl.nasa.gov |
| Pseudocode | No | The paper describes the algorithm in text and with a schematic diagram (Figure 3), but it does not include formal pseudocode or an algorithm block. |
| Open Source Code | No | The paper does not provide an explicit statement about the release of its source code, nor does it provide a link to a code repository for the methodology described. |
| Open Datasets | Yes | To evaluate the ability of our proposed precision targeting approach to identify targets in an RMI image and to characterize the factors that affect its performance, we used over 3,800 images acquired by the MSL rover during the first 1,200 sols of operation. Images are made publicly accessible online via the Planetary Data System [Wiens, 2013]. [Wiens, 2013] R. C. Wiens. MSL Chem Cam remote micro-imaging camera raw data. https://pds.jpl.nasa.gov/dsview/pds/viewDataset.jsp?dsid=MSL-M-CHEMCAMRMI-2-EDR-V1.0, 2013. NASA Planetary Data System. |
| Dataset Splits | No | The paper describes how the training examples for the random forest classifier were identified and used, including evaluation 'using the labels on the training examples when they are left out of bootstrap samples,' but it does not specify explicit numerical splits (percentages or counts) for train/validation/test sets for the primary image data. |
| Hardware Specification | Yes | Finally, we have implemented a C++ version of our precision targeting algorithm, with running times of less than 1 minute with over 3,500 landmarks on a 150 MHz LEON4 processor, which is comparable to the processing capability of the rover s on-board processor. |
| Software Dependencies | No | The paper mentions using 'the Open CV implementation of ORB feature extraction and RANSAC-based homography finding', but it does not provide specific version numbers for OpenCV or any other software libraries. |
| Experiment Setup | Yes | A random forest with 100 trees was used to classify the homographies produced by the process in Figure 3. The algorithm was rerun with different numbers of landmarks ranging from 50 to 3,500. |