Marine Robotics Group
The Marine Robotics Group, headed by Prof. John J. Leonard, is part of the Computer Science and Artificial Intelligence Laboratory in MIT. Our research addresses the problems of navigation and mapping for autonomous mobile operating in underwater and terrestrial environments. A primary goal of our ongoing research is persistent autonomy --- the capability for one or more robots to operate robustly for days, weeks and months at a time with minimal human supervision, in complex, dynamic environments. Taking the limit as time goes to infinity poses difficult challenges to our algorithms, but this is imperative for many applications of autonomous mobile robots. For example, security missions require the capability for robots to build and maintain maps of large areas, detecting changes and correcting their internal representations to maintain currency with the world.
A listing of current and recent projects and publications is given below.
Contents |
News
April, 2013: University of Minnesota DTC Science and Technology Innovators Lecture Series Seminar: http://www.dtc.umn.edu/seminars/events.php?eventdesc=695 Watch online: https://umconnect.umn.edu/p88685496/
January, 2013: Hordur Johannsson successfully defended his PhD Thesis "Toward Lifelong Visual Localization and Mapping" pdf
January, 2013: Our group has had three papers accepted for ICRA 2013:
- H. Johannsson, M. Kaess, M.F. Fallon, and J.J. Leonard. Temporally scalable visual SLAM using a reduced pose graph. pdf bibtex
- D.M. Rosen, M. Kaess, and J.J. Leonard. Robust incremental online inference over sparse factor graphs: Beyond the Gaussian case. pdf bibtex
- T. Whelan, H. Johannsson, M. Kaess, J.J. Leonard, and J.B. McDonald. Robust Real-Time Visual Odometry for Dense RGB-D Mapping. pdf bibtex video
Current Projects
- Temporally Scalable Visual SLAM video
- Spatially Extended Kinect Fusion (in collaboration with Tom Whelan and John McDonald at NUIM) video
- Feature-based Navigation for AUVs
- ONR GridCell MURI (PI: Mike Hasselmo at Boston University)
- ONR Non-Parametric Bayes MURI (PI: Jon How at MIT LIDS)
- SPHERES/Vertigo (in collaboration with the MIT Space Systems Laboratory)
Previous Projects
 |
Videos
|
Multiple Relative Pose Graphs for Robust Cooperative Mapping (ICRA 2010) |
Multiple Relative Pose Graphs for Robust Cooperative Mapping
Abstract— This paper describes a new algorithm for cooperative and persistent simultaneous localization and mapping (SLAM) using multiple robots. Recent pose graph representations have proven very successful for single robot mapping and localization. Among these methods, incremental smoothing and mapping (iSAM) gives an exact incremental solution to the SLAM problem by solving a full nonlinear optimization problem in real-time. In this paper, we present a novel extension to iSAM to facilitate online multi-robot mapping based on multiple pose graphs. Our main contribution is a relative formulation of the relationship between multiple pose graphs that avoids the initialization problem and leads to an efficient solution when compared to a completely global formulation. The relative pose graphs are optimized together to provide a globally consistent multi-robot solution. Efficient access to covariances at any time for relative parameters is provided through iSAM, facilitating data association and loop closing. The performance of the technique is illustrated on various data sets including a publicly available multi-robot data set. Further evaluation is performed in a collaborative helicopter and ground robot experiment. pdf bibtex |
|
Acoustic Modem Cooperative Navigation (ICRA 2011) |
A Measurement Distribution Framework for Cooperative Navigation using Multiple AUVs
Abstract— In recent years underwater survey and surveillance missions with more than a single Autonomous Underwater Vehicle (AUV) have become more common thanks to more reliable and cheaper platforms, as well as the addition of remote command and control communications using, for example, the WHOI acoustic modem. However cooperative navigation of AUVs has thus far been limited to a single AUV supported by a dedicated surface vehicle with access to GPS. In this paper a scalable and modular framework is presented in which any number of vehicles can broadcast, forward and acknowledge range, dead-reckoning, feature and GPS measurements so that the full fleet of AUVs can navigate and cooperate in a consistent and accurate manner. The approach is independent of the resultant application — such as recursive state estimation or full pose optimization. Trade-offs between the number of vehicles, the condition of the communication channel and rate at which updates are available are also discussed. Finally performance is illustrated in a realistic experiment. pdf bibtex |
|
Imaging Sonar-Aided Navigation for AUVs (IROS 2010) |
Imaging Sonar-Aided Navigation for Autonomous Underwater Harbor Surveillance
Abstract— In this paper we address the problem of driftfree navigation for underwater vehicles performing harbor surveillance and ship hull inspection. Maintaining accurate localization for the duration of a mission is important for a variety of tasks, such as planning the vehicle trajectory and ensuring coverage of the area to be inspected. Our approach only uses onboard sensors in a simultaneous localization and mapping setting and removes the need for any external infrastructure like acoustic beacons. We extract dense features from a forwardlooking imaging sonar and apply pair-wise registration between sonar frames. The registrations are combined with onboard velocity, attitude and acceleration sensors to obtain an improved estimate of the vehicle trajectory. We show results from several experiments that demonstrate drift-free navigation in various underwater environments. pdf bibtex |
Directions
- Prof Leonard's Office Room: 32-231
- Group Office Space: 32-225
- Group Lab Space: 32-271
