Maurice Fallon

Bio: Maurice Fallon is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Robot. The author has an hindex of 29, co-authored 98 publications receiving 4009 citations. Previous affiliations of Maurice Fallon include Massachusetts Institute of Technology & University of Edinburgh.

Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot

Abstract: This paper describes a collection of optimization algorithms for achieving dynamic planning, control, and state estimation for a bipedal robot designed to operate reliably in complex environments. To make challenging locomotion tasks tractable, we describe several novel applications of convex, mixed-integer, and sparse nonlinear optimization to problems ranging from footstep placement to whole-body planning and control. We also present a state estimator formulation that, when combined with our walking controller, permits highly precise execution of extended walking plans over non-flat terrain. We describe our complete system integration and experiments carried out on Atlas, a full-size hydraulic humanoid robot built by Boston Dynamics, Inc.

Kintinuous: Spatially Extended KinectFusion

Abstract: In this paper we present an extension to the KinectFusion algorithm that permits dense mesh-based mapping of extended scale environments in real-time. This is achieved through (i) altering the original algorithm such that the region of space being mapped by the KinectFusion algorithm can vary dynamically, (ii) extracting a dense point cloud from the regions that leave the KinectFusion volume due to this variation, and, (iii) incrementally adding the resulting points to a triangular mesh representation of the environment. The system is implemented as a set of hierarchical multi-threaded components which are capable of operating in real-time. The architecture facilitates the creation and integration of new modules with minimal impact on the performance on the dense volume tracking and surface reconstruction modules. We provide experimental results demonstrating the system’s ability to map areas considerably beyond the scale of the original KinectFusion algorithm including a two story apartment and an extended sequence taken from a car at night. In order to overcome failure of the iterative closest point (ICP) based odometry in areas of low geometric features we have evaluated the Fast Odometry from Vision (FOVIS) system as an alternative. We provide a comparison between the two approaches where we show a trade off between the reduced drift of the visual odometry approach and the higher local mesh quality of the ICP-based approach. Finally we present ongoing work on incorporating full simultaneous localisation and mapping (SLAM) pose-graph optimisation.

Real-time large-scale dense RGB-D SLAM with volumetric fusion

Abstract: We present a new simultaneous localization and mapping SLAM system capable of producing high-quality globally consistent surface reconstructions over hundreds of meters in real time with only a low-cost commodity RGB-D sensor. By using a fused volumetric surface reconstruction we achieve a much higher quality map over what would be achieved using raw RGB-D point clouds. In this paper we highlight three key techniques associated with applying a volumetric fusion-based mapping system to the SLAM problem in real time. First, the use of a GPU-based 3D cyclical buffer trick to efficiently extend dense every-frame volumetric fusion of depth maps to function over an unbounded spatial region. Second, overcoming camera pose estimation limitations in a wide variety of environments by combining both dense geometric and photometric camera pose constraints. Third, efficiently updating the dense map according to place recognition and subsequent loop closure constraints by the use of an 'as-rigid-as-possible' space deformation. We present results on a wide variety of aspects of the system and show through evaluation on de facto standard RGB-D benchmarks that our system performs strongly in terms of trajectory estimation, map quality and computational performance in comparison to other state-of-the-art systems.

Real-time large-scale dense RGB-D SLAM with volumetric fusion

Abstract: We present a new simultaneous localization and mapping SLAM system capable of producing high-quality globally consistent surface reconstructions over hundreds of meters in real time with only a low-cost commodity RGB-D sensor. By using a fused volumetric surface reconstruction we achieve a much higher quality map over what would be achieved using raw RGB-D point clouds. In this paper we highlight three key techniques associated with applying a volumetric fusion-based mapping system to the SLAM problem in real time. First, the use of a GPU-based 3D cyclical buffer trick to efficiently extend dense every-frame volumetric fusion of depth maps to function over an unbounded spatial region. Second, overcoming camera pose estimation limitations in a wide variety of environments by combining both dense geometric and photometric camera pose constraints. Third, efficiently updating the dense map according to place recognition and subsequent loop closure constraints by the use of an 'as-rigid-as-possible' space deformation. We present results on a wide variety of aspects of the system and show through evaluation on de facto standard RGB-D benchmarks that our system performs strongly in terms of trajectory estimation, map quality and computational performance in comparison to other state-of-the-art systems.

Cooperative AUV Navigation using a Single Maneuvering Surface Craft

Abstract: In this paper we describe the experimental implementation of an online algorithm for cooperative localization of submerged autonomous underwater vehicles (AUVs) supported by an autonomous surface craft. Maintaining accurate localization of an AUV is difficult because electronic signals, such as GPS, are highly attenuated by water. The usual solution to the problem is to utilize expensive navigation sensors to slow the rate of dead-reckoning divergence. We investigate an alternative approach that utilizes the position information of a surface vehicle to bound the error and uncertainty of the on-board position estimates of a low-cost AUV. This approach uses the Woods Hole Oceanographic Institution (WHOI) acoustic modem to exchange vehicle location estimates while simultaneously estimating inter-vehicle range. A study of the system observability is presented so as to motivate both the choice of filtering approach and surface vehicle path planning. The first contribution of this paper is to the presentation of an experiment in which an extended Kalman filter (EKF) implementation of the concept ran online on-board an OceanServer Iver2 AUV while supported by an autonomous surface vehicle moving adaptively. The second contribution of this paper is to provide a quantitative performance comparison of three estimators: particle filtering (PF), non-linear least-squares optimization (NLS), and the EKF for a mission using three autonomous surface craft (two operating in the AUV role). Our results indicate that the PF and NLS estimators outperform the EKF, with NLS providing the best performance.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras

Abstract: We present ORB-SLAM2, a complete simultaneous localization and mapping (SLAM) system for monocular, stereo and RGB-D cameras, including map reuse, loop closing, and relocalization capabilities. The system works in real time on standard central processing units in a wide variety of environments from small hand-held indoors sequences, to drones flying in industrial environments and cars driving around a city. Our back-end, based on bundle adjustment with monocular and stereo observations, allows for accurate trajectory estimation with metric scale. Our system includes a lightweight localization mode that leverages visual odometry tracks for unmapped regions and matches with map points that allow for zero-drift localization. The evaluation on 29 popular public sequences shows that our method achieves state-of-the-art accuracy, being in most cases the most accurate SLAM solution. We publish the source code, not only for the benefit of the SLAM community, but with the aim of being an out-of-the-box SLAM solution for researchers in other fields.

ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras

Abstract: We present ORB-SLAM2 a complete SLAM system for monocular, stereo and RGB-D cameras, including map reuse, loop closing and relocalization capabilities. The system works in real-time on standard CPUs in a wide variety of environments from small hand-held indoors sequences, to drones flying in industrial environments and cars driving around a city. Our back-end based on bundle adjustment with monocular and stereo observations allows for accurate trajectory estimation with metric scale. Our system includes a lightweight localization mode that leverages visual odometry tracks for unmapped regions and matches to map points that allow for zero-drift localization. The evaluation on 29 popular public sequences shows that our method achieves state-of-the-art accuracy, being in most cases the most accurate SLAM solution. We publish the source code, not only for the benefit of the SLAM community, but with the aim of being an out-of-the-box SLAM solution for researchers in other fields.

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes

Abstract: A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available – current datasets cover a small range of scene views and have limited semantic annotations. To address this issue, we introduce ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations. To collect this data, we designed an easy-to-use and scalable RGB-D capture system that includes automated surface reconstruction and crowdsourced semantic annotation. We show that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks, including 3D object classification, semantic voxel labeling, and CAD model retrieval.