Search NASA⌕ Search

SEARCH · Search NASA

Results for “visual odometry”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2012

Localization Using Visual Odometry and a Single Downward-Pointing Camera

Stereo imaging is a technique commonly employed for vision-based navigation. For such applications, two images are acquired from different vantage points and then compared using transformations to extract depth information. The technique is commonly used in robotics for obstacle avoidance or for Simultaneous Localization And Mapping, (SLAM). Yet, the process requires a number of image processing steps and therefore tends to be CPU-intensive, which limits the real-time data rate and use in power-limited applications. Evaluated here is a technique where a monocular camera is used for vision-based odometry. In this work, an optical flow technique with feature recognition is performed to generate odometry measurements. The visual odometry sensor measurements are intended to be used as control inputs or measurements in a sensor fusion algorithm using low-cost MEMS based inertial sensors to provide improved localization information. Presented here are visual odometry results which demonstrate the challenges associated with using ground-pointing cameras for visual odometry. The focus is for rover-based robotic applications for localization within GPS-denied environments.

Swank, Aaron J.↗
NASA NTRS2016

Visual Odometry for Autonomous Deep-Space Navigation

Visual Odometry fills two critical needs shared by all future exploration architectures considered by NASA: Autonomous Rendezvous and Docking (AR&D), and autonomous navigation during loss of comm. To do this, a camera is combined with cutting-edge algorithms (called Visual Odometry) into a unit that provides accurate relative pose between the camera and the object in the imagery. Recent simulation analyses have demonstrated the ability of this new technology to reliably, accurately, and quickly compute a relative pose. This project advances this technology by both preparing the system to process flight imagery and creating an activity to capture said imagery. This technology can provide a pioneering optical navigation platform capable of supporting a wide variety of future missions scenarios: deep space rendezvous, asteroid exploration, loss-of-comm.

Robinson, Shane↗
NASA NTRS2004

Path following using visual odometry for Mars Rover in high-slip environments.

An architecture for autonomous operation of Mars rovers in high slip environments has been designed, implemented, and tested. This architecture is composed of several key technologies that enable the rover to accurately follow a designated path, compensate for slippage, and reach intended goals independent of the terrain over which it is traversing (within the mechanical constraints of the mobility system). These technologies include: visual odometry, full vehicle kinematics, a Kalman filter, and a slop compensation/path follower. Visual odometry tracks distinctive scene features in stereo imagery to estimate rover motion between successively acquired stereo image pairs using a maximum likelihood motion estimation algorithm. The full vehicle kinematics for a rocker-bogie suspension system estimates motion, with a no-slip assumption, by measuring wheel, rates, and rocker, bogie, and steering angles. The Kalman filter merges data from an Inertial Measurement Unit (IMU) and visual odometry. This merged estimate is then compared to the kinematic estimate to determining (tracking into account estimate uncertainties) if and how much slippage has occurred then a slip vector is calculated by differencing the current Kalman filter estimate from the kinematic estimate. This slip vector is then used, in conjunction with the inverse kinematics, to determine the necessary wheel velocities and steering angles to compensate for slip and follow the desired path.

Roumeliotis, Stergios I.↗
NASA NTRS2016

Visual Odometry for Autonomous Deep-Space Navigation Project

Autonomous rendezvous and docking (AR&D) is a critical need for manned spaceflight, especially in deep space where communication delays essentially leave crews on their own for critical operations like docking. Previously developed AR&D sensors have been large, heavy, power-hungry, and may still require further development (e.g. Flash LiDAR). Other approaches to vision-based navigation are not computationally efficient enough to operate quickly on slower, flight-like computers. The key technical challenge for visual odometry is to adapt it from the current terrestrial applications it was designed for to function in the harsh lighting conditions of space. This effort leveraged Draper Laboratory’s considerable prior development and expertise, benefitting both parties. The algorithm Draper has created is unique from other pose estimation efforts as it has a comparatively small computational footprint (suitable for use onboard a spacecraft, unlike alternatives) and potentially offers accuracy and precision needed for docking. This presents a solution to the AR&D problem that only requires a camera, which is much smaller, lighter, and requires far less power than competing AR&D sensors. We have demonstrated the algorithm’s performance and ability to process ‘flight-like’ imagery formats with a ‘flight-like’ trajectory, positioning ourselves to easily process flight data from the upcoming ‘ISS Selfie’ activity and then compare the algorithm’s quantified performance to the simulated imagery. This will bring visual odometry beyond TRL 5, proving its readiness to be demonstrated as part of an integrated system.Once beyond TRL 5, visual odometry will be poised to be demonstrated as part of a system in an in-space demo where relative pose is critical, like Orion AR&D, ISS robotic operations, asteroid proximity operations, and more.

Robinson, Shane↗
NASA NTRS2016

Visual Odometry for Autonomous Deep-Space Navigation Project

Autonomous rendezvous and docking (AR&D) is a critical need for manned spaceflight, especially in deep space where communication delays essentially leave crews on their own for critical operations like docking. Previously developed AR&D sensors have been large, heavy, power-hungry, and may still require further development (e.g. Flash LiDAR). Other approaches to vision-based navigation are not computationally efficient enough to operate quickly on slower, flight-like computers. The key technical challenge for visual odometry is to adapt it from the current terrestrial applications it was designed for to function in the harsh lighting conditions of space. This effort leveraged Draper Laboratory's considerable prior development and expertise, benefitting both parties. The algorithm Draper has created is unique from other pose estimation efforts as it has a comparatively small computational footprint (suitable for use onboard a spacecraft, unlike alternatives) and potentially offers accuracy and precision needed for docking. This presents a solution to the AR&D problem that only requires a camera, which is much smaller, lighter, and requires far less power than competing AR&D sensors. We have demonstrated the algorithm's performance and ability to process 'flight-like' imagery formats with a 'flight-like' trajectory, positioning ourselves to easily process flight data from the upcoming 'ISS Selfie' activity and then compare the algorithm's quantified performance to the simulated imagery. This will bring visual odometry beyond TRL 5, proving its readiness to be demonstrated as part of an integrated system. Once beyond TRL 5, visual odometry will be poised to be demonstrated as part of a system in an in-space demo where relative pose is critical, like Orion AR&D, ISS robotic operations, asteroid proximity operations, and more.

Robinson, Shane↗
NASA NTRS2005

Visual odometry on the Mars Exploration Rovers

In this paper we describe the Visual Odometry algorithm used on the Mars Exploration Rovers, and summarize the results obtained by running this processing onboard during the first year of operations on Mars.

egomotion↗
NASA NTRS2004

Realtime Absolute Orientation with Outlier Rejection for Visual Odometry and Mesh Merging

This paper addresses a high level spatio-temporal problem, namely "absolute orientation", which arises in visual-odometry (using stereo), or registering two models created by different Structure from Motion (SFM) reconstructions. We compare the very popular method due to Horn using quaternions and our own independently derive method using the orthonormal rotation matrix R. We also introduce a novel approach for outlier rejection using spectral clustering.

Bandari, Esfandiar↗
NASA NTRS2021

Unsupervised Deep Persistent Monocular Visual Odometry and Depth Estimation in Extreme Environments

In recent years, unsupervised deep learning ap-proaches have received a significant attention to estimate depthand visual odometry (VO) from unlabelled monocular imagesequences. However, their performance is limited in challengingenvironments due to perceptual degradation, occlusions andrapid motions. Moreover, the existing unsupervised methodssuffer from the lack of scale-consistency constraints acrossframes, which causes that the VO estimators fail to providepersistent trajectories over long sequences. In this study, wepropose a unsupervised monocular deep VO framework thatpredicts 6 degrees-of-freedom pose camera motion and depthmap of the scene from unlabelled RGB image sequences.We provide detailed quantitative and qualitative evaluationsof the proposed framework on a) a challenging dataset col-lected during the DARPA Subterranean challenge1; and b)the benchmark KITTI and Cityscapes datasets. The proposedapproach outperforms both traditional and state-of-the-artunsupervised deep VO methods providing better results for bothpose estimation and depth recovery. The presented approach ispart of the solution used by the COSTAR team participatingat the DARPA Subterranean Challenge

Agha-mohammadi, Ali-akbar↗
NASA NTRS2022

Visual Odometry Thinking While Driving for the Curiosity Mars Rover's Three-Year Test Campaign: Impact of Evolving Constraints on Verification and Validation

Over the first 9 years of the Mars Science Laboratory (MSL) Curiosity rover's surface mission, more than 87\% of its driving has been performed using Visual Odometry (VO). The benefits of using VO during driving are that it minimizes rover position uncertainty and can be used to monitor wheel slip, halting a drive if excessive wheel slip is occurring. The VO implementation on board Curiosity acquires and processes VO images in between drive steps while the rover is stationary. A VO Thinking While Driving (VTWD) flight software capability has been developed which enables the processing of VO images during rover driving, increasing the distance Curiosity can drive with VO in a given time period up to as much as 1.75x total distance. Verification and Validation (V\&V) of the capability has been challenging due to impacts from the COVID-19 pandemic and unavailability of the JPL Mars Yard outdoor test site. The VTWD V\&V test procedures were modified to use a small indoor space with Mars-like terrain. This paper describes the 3 year V\&V effort under challenging conditions to approve the VTWD capability for use on the Curiosity rover.

Rankin, Arturo↗
NASA NTRS2012

Stereo and IMU-Assisted Visual Odometry for Small Robots

This software performs two functions: (1) taking stereo image pairs as input, it computes stereo disparity maps from them by cross-correlation to achieve 3D (three-dimensional) perception; (2) taking a sequence of stereo image pairs as input, it tracks features in the image sequence to estimate the motion of the cameras between successive image pairs. A real-time stereo vision system with IMU (inertial measurement unit)-assisted visual odometry was implemented on a single 750 MHz/520 MHz OMAP3530 SoC (system on chip) from TI (Texas Instruments). Frame rates of 46 fps (frames per second) were achieved at QVGA (Quarter Video Graphics Array i.e. 320 240), or 8 fps at VGA (Video Graphics Array 640 480) resolutions, while simultaneously tracking up to 200 features, taking full advantage of the OMAP3530's integer DSP (digital signal processor) and floating point ARM processors. This is a substantial advancement over previous work as the stereo implementation produces 146 Mde/s (millions of disparities evaluated per second) in 2.5W, yielding a stereo energy efficiency of 58.8 Mde/J, which is 3.75 better than prior DSP stereo while providing more functionality.

Source record↗
NASA NTRS2007

Using Visual Odometry to Estimate Position and Attitude

A computer program in the guidance system of a mobile robot generates estimates of the position and attitude of the robot, using features of the terrain on which the robot is moving, by processing digitized images acquired by a stereoscopic pair of electronic cameras mounted rigidly on the robot. Developed for use in localizing the Mars Exploration Rover (MER) vehicles on Martian terrain, the program can also be used for similar purposes on terrestrial robots moving in sufficiently visually textured environments: examples include low-flying robotic aircraft and wheeled robots moving on rocky terrain or inside buildings. In simplified terms, the program automatically detects visual features and tracks them across stereoscopic pairs of images acquired by the cameras. The 3D locations of the tracked features are then robustly processed into an estimate of overall vehicle motion. Testing has shown that by use of this software, the error in the estimate of the position of the robot can be limited to no more than 2 percent of the distance traveled, provided that the terrain is sufficiently rich in features. This software has proven extremely useful on the MER vehicles during driving on sandy and highly sloped terrains on Mars.

Maimone, Mark↗
NASA NTRS2016

Motion Estimation Utilizing Range Detection-Enhanced Visual Odometry

A motion determination system is disclosed. The system may receive a first and a second camera image from a camera, the first camera image received earlier than the second camera image. The system may identify corresponding features in the first and second camera images. The system may receive range data comprising at least one of a first and a second range data from a range detection unit, corresponding to the first and second camera images, respectively. The system may determine first positions and the second positions of the corresponding features using the first camera image and the second camera image. The first positions or the second positions may be determined by also using the range data. The system may determine a change in position of the machine based on differences between the first and second positions, and a VO-based velocity of the machine based on the determined change in position.

Friend, Paul Russell↗
NASA NTRS2022

Lunar Rover Localization Using Craters as Landmarks

Onboard localization capabilities for planetary rovers to date have used relative navigation, by integrating combinations of wheel odometry, visual odometry, and inertial measurements during each drive to track position relative to the start of each drive. At the end of each drive, a “ground-in-the-loop” (GITL) interaction is used to get a position update from human operators in a more global reference frame, such as a map frame defined by orbital reconnaissance imaging of a large region around the rover’s current position. For Mars rovers, this typically has involved downlinking imagery from the rover mast cameras and using interactive visualization tools on Earth to register such images to the orbital reconnaissance images. For safety purposes, rover mission operations typically specify “keep out zones”, which human operators recognize as being unsafe in the orbital images. Autonomous rover drives are limited in distance so that accumulated relative navigation error does not risk the possibility of the rover driving into a keep out zone. The allowable autonomous drive distance in this mode of operation depends on the distribution of keep out zones and the accuracy of relative navigation; in practice, drive limits of a few hundred meters between GITL cycles are to be expected. Several rover mission concepts have recently been studied that require much longer drives between GITL cycles, particularly for the Moon. This includes lunar rover mission concepts that involve (1) driving mostly in sunlight at low latitudes, (2) driving in permanently shadowed regions near the south pole, and (3) a mixture of day and night driving in mid-latitudes. These concepts include total traverse distance requirements of up to 1,800 km in 4 Earth years, with individual drives of several kilometers between stops for downlink. These concepts require greater autonomy to minimize GITL cycles to enable such large range; onboard global localization is a key element of such autonomy. Multiple techniques have been studied in the past for onboard rover global localization, including radio navigation aiding from an orbiter, recognizing horizon landmarks that are known in a regional elevation map, and correlating a local elevation map created onboard the rover with a regional elevation map. These techniques all have drawbacks, including requiring an expensive extra mission element (navigation orbiter), unavailability of sufficient regional elevation map data, or limited accuracy in resulting position estimates (e.g. a few hundred meters with horizon landmarks). For the Moon, the ubiquitous craters offer another possibility, which involves mapping craters from orbit, then recognizing crater landmarks with cameras and/or a lidar onboard the rover. This approach is applicable everywhere on the Moon, does not require high resolution stereo imaging from orbit as some other approaches do, and has potential to enable position knowledge with order of 10 m accuracy at all times. This paper will provide more detail on our technical approach to crater-based lunar rover localization and will present initial results on crater detection using 3-D point cloud data from onboard lidar or stereo cameras and using shading cues in monocular onboard imagery.

Ono, M.↗
NASA NTRS2008

Vision System Measures Motions of Robot and External Objects

A prototype of an advanced robotic vision system both (1) measures its own motion with respect to a stationary background and (2) detects other moving objects and estimates their motions, all by use of visual cues. Like some prior robotic and other optoelectronic vision systems, this system is based partly on concepts of optical flow and visual odometry. Whereas prior optoelectronic visual-odometry systems have been limited to frame rates of no more than 1 Hz, a visual-odometry subsystem that is part of this system operates at a frame rate of 60 to 200 Hz, given optical-flow estimates. The overall system operates at an effective frame rate of 12 Hz. Moreover, unlike prior machine-vision systems for detecting motions of external objects, this system need not remain stationary: it can detect such motions while it is moving (even vibrating). The system includes a stereoscopic pair of cameras mounted on a moving robot. The outputs of the cameras are digitized, then processed to extract positions and velocities. The initial image-data-processing functions of this system are the same as those of some prior systems: Stereoscopy is used to compute three-dimensional (3D) positions for all pixels in the camera images. For each pixel of each image, optical flow between successive image frames is used to compute the two-dimensional (2D) apparent relative translational motion of the point transverse to the line of sight of the camera. The challenge in designing this system was to provide for utilization of the 3D information from stereoscopy in conjunction with the 2D information from optical flow to distinguish between motion of the camera pair and motions of external objects, compute the motion of the camera pair in all six degrees of translational and rotational freedom, and robustly estimate the motions of external objects, all in real time. To meet this challenge, the system is designed to perform the following image-data-processing functions: The visual-odometry subsystem (the subsystem that estimates the motion of the camera pair relative to the stationary background) utilizes the 3D information from stereoscopy and the 2D information from optical flow. It computes the relationship between the 3D and 2D motions and uses a least-mean-squares technique to estimate motion parameters. The least-mean-squares technique is suitable for real-time implementation when the number of external-moving-object pixels is smaller than the number of stationary-background pixels.

Talukder, Ashit↗
NASA NTRS2005

Path Following with Slip Compensation for a Mars Rover

A software system for autonomous operation of a Mars rover is composed of several key algorithms that enable the rover to accurately follow a designated path, compensate for slippage of its wheels on terrain, and reach intended goals. The techniques implemented by the algorithms are visual odometry, full vehicle kinematics, a Kalman filter, and path following with slip compensation. The visual-odometry algorithm tracks distinctive scene features in stereo imagery to estimate rover motion between successively acquired stereo image pairs, by use of a maximum-likelihood motion-estimation algorithm. The full-vehicle kinematics algorithm estimates motion, with a no-slip assumption, from measured wheel rates, steering angles, and angles of rockers and bogies in the rover suspension system. The Kalman filter merges data from an inertial measurement unit (IMU) and the visual-odometry algorithm. The merged estimate is then compared to the kinematic estimate to determine whether and how much slippage has occurred. The kinematic estimate is used to complement the Kalman-filter estimate if no statistically significant slippage has occurred. If slippage has occurred, then a slip vector is calculated by subtracting the current Kalman filter estimate from the kinematic estimate. This slip vector is then used, in conjunction with the inverse kinematics, to determine the wheel velocities and steering angles needed to compensate for slip and follow the desired path.

Helmick, Daniel↗
NASA NTRS2007

Robotic Vision-Based Localization in an Urban Environment

A system of electronic hardware and software, now undergoing development, automatically estimates the location of a robotic land vehicle in an urban environment using a somewhat imprecise map, which has been generated in advance from aerial imagery. This system does not utilize the Global Positioning System and does not include any odometry, inertial measurement units, or any other sensors except a stereoscopic pair of black-and-white digital video cameras mounted on the vehicle. Of course, the system also includes a computer running software that processes the video image data. The software consists mostly of three components corresponding to the three major image-data-processing functions: Visual Odometry This component automatically tracks point features in the imagery and computes the relative motion of the cameras between sequential image frames. This component incorporates a modified version of a visual-odometry algorithm originally published in 1989. The algorithm selects point features, performs multiresolution area-correlation computations to match the features in stereoscopic images, tracks the features through the sequence of images, and uses the tracking results to estimate the six-degree-of-freedom motion of the camera between consecutive stereoscopic pairs of images (see figure). Urban Feature Detection and Ranging Using the same data as those processed by the visual-odometry component, this component strives to determine the three-dimensional (3D) coordinates of vertical and horizontal lines that are likely to be parts of, or close to, the exterior surfaces of buildings. The basic sequence of processes performed by this component is the following: 1. An edge-detection algorithm is applied, yielding a set of linked lists of edge pixels, a horizontal-gradient image, and a vertical-gradient image. 2. Straight-line segments of edges are extracted from the linked lists generated in step 1. Any straight-line segments longer than an arbitrary threshold (e.g., 30 pixels) are assumed to belong to buildings or other artificial objects. 3. A gradient-filter algorithm is used to test straight-line segments longer than the threshold to determine whether they represent edges of natural or artificial objects. In somewhat oversimplified terms, the test is based on the assumption that the gradient of image intensity varies little along a segment that represents the edge of an artificial object.

Mchenry, Michael↗
NASA NTRS2006

Tracking Positions and Attitudes of Mars Rovers

The Surface Attitude Position and Pointing (SAPP) software, which runs on computers aboard the Mars Exploration Rovers, tracks the positions and attitudes of the rovers on the surface of Mars. Each rover acquires data on attitude from a combination of accelerometer readings and images of the Sun acquired autonomously, using a pointable camera to search the sky for the Sun. Depending on the nature of movement commanded remotely by operators on Earth, the software propagates attitude and position by use of either (1) accelerometer and gyroscope readings or (2) gyroscope readings and wheel odometry. Where necessary, visual odometry is performed on images to fine-tune the position updates, particularly on high-wheel-slip terrain. The attitude data are used by other software and ground-based personnel for pointing a high-gain antenna, planning and execution of driving, and positioning and aiming scientific instruments.

Ali, Khaled↗