Two years of Visual Odometry on the Mars Exploration Rovers

By Mark W. Maimone, Yang Cheng, Larry H. Matthies. J. Field Robotics, 2007

748 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6c04fe696ac95b41532650f3eb521ba6a7411ef4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Visual teach and repeat for long‐range rover autonomy (2010, methodology): “We use the frame-to-frame VO method described by Maimone, Cheng, and Matthies (2007).”
Spirit Mars Rover Mission: Overview and selected results from the northern Home Plate Winter Haven to the side of Scamander crater (2010, methodology): “[7] Even though yaw changes were minimized during backward drives, visual odometry was often utilized during five‐wheel drive sessions to help keep Spirit on a predefined course, both for fine maneuvering to targets and for long drives in complex terrains [Maimone et al., 2007].”
SVO: Semidirect Visual Odometry for Monocular and Multicamera Systems (2017, background): “, in scenes with little or high-frequency texture (such as sand [12] or asphalt [13]), is increased when the algorithm is not restricted to use local point features (e.”
Visual-lidar odometry and mapping: low-drift, robust, and fast (2015, background): “With stereo cameras [3], [4], the baseline provides a reference to help determine scale of the motion.”
Made to measure: Bespoke landmarks for 24-hour, all-weather localisation with a camera (2016, methodology): “The pose optimisation is performed in a similar manner to [28][29][30].”
Real-time stereo visual odometry for autonomous ground vehicles (2008, background): “Visual odometry, which estimates vehicle motion from a sequence of camera images, offers a natural complement to these sensors: it is insensitive to soil mechanics, produces a full 6DOF motion estimate, and has lower drift rates than all but the most expensive IMUs.”
A multirange architecture for collision‐free off‐road robot navigation (2009, methodology): “The NASA Mars Exploration Vehicle is hit particularly hard by the computational demands of full VO, which can take up to 3 minutes per frame on its 20 MHz processor, leading to an average movement of 10m/hour (Maimone et al., 2007).”
Selection of the Mars Science Laboratory Landing Site (2012, methodology): “MSL flight software, like MER flight software, includes two autonomous mobility modes: Autonomous Navigation (AutoNav) and visual odometry (Visodom) (Maimone et al. 2006, 2007a, 2007b).”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “, Mars rovers [166], domestic robots [2]), and visual-inertial odometry [95] can be considered mature research fields.”