A5050308210- Robotics and Sensor-Based Localization
- Underwater Vehicles and Communication Systems
- Robotic Path Planning Algorithms
- Advanced Vision and Imaging
- Software Engineering Techniques and Practices
- Modular Robots and Swarm Intelligence
- Advanced Image and Video Retrieval Techniques
- Robotics and Automated Systems
- Software Engineering Research
- 3D Surveying and Cultural Heritage
- Underwater Acoustics Research
- Advanced Software Engineering Methodologies
- Business Process Modeling and Analysis
- Indoor and Outdoor Localization Technologies
- Water Quality Monitoring Technologies
- Advanced Optical Sensing Technologies
- Maritime Navigation and Safety
- Robot Manipulation and Learning
- Optimization and Search Problems
- Image and Object Detection Techniques
- Digital Innovation in Industries
- Remote Sensing and LiDAR Applications
- Reinforcement Learning in Robotics
- Flexible and Reconfigurable Manufacturing Systems
- Image Retrieval and Classification Techniques
Software (Germany)
2007-2024
Constructor University
2015-2024
Robotics Research (United States)
2023
University of Bremen
2005-2015
Vrije Universiteit Brussel
1996-2007
International University
2002-2007
Fraunhofer Institute for Experimental Software Engineering
1998-2001
DEVCOM Army Research Laboratory
1988-2001
Flemish Community
2001
Fraunhofer Society
1997-2000
Mapping can potentially be speeded up in a significant way by using multiple robots exploring different parts of the environment. But core question multirobot mapping is how to integrate data into single global map. A amount research exists area that deals with techniques estimate relative poses at start or during process. With map merging, contrast individually build local maps without any knowledge about their positions. The goal then identify regions overlap which joined together....
We present a robot-pose-registration algorithm, which is entirely based on large planar-surface patches extracted from point clouds sampled three-dimensional (3-D) sensor. This approach offers an alternative to the traditional point-to-point iterative-closest-point (ICP) its point-to-plane variant, as well newer grid-based algorithms, such 3-D normal distribution transform (NDT). The simpler case of known plane correspondences tackled first by deriving expressions for least-squares pose...
A fast but nevertheless accurate approach for surface extraction from noisy 3D point clouds is presented. It consists of two parts, namely a plane fitting and polygonalization step. Both exploit the sequential nature data acquisition on mobile robots in form range images. For fitting, this used to revise standard mathematical formulation an incremental version, which allows linear computation. polygonalization, neighborhood relation images exploited. Experiments are presented using...
Postmortem analysis (PMA) is a practical method for initiating knowledge management by capturing experience and improvement suggestions from completed projects. It requires little effort quickly provides initial results, making it suitable even small- medium-size projects companies. The authors describe their experiences with applying PMA techniques collecting analyzing in software organizations.
Abstract A fast pose‐graph relaxation technique is presented for enhancing the consistency of three‐dimensional (3D) maps created by registering large planar surface patches. The patches are extracted from point clouds sampled a 3D range sensor. plane‐based registration method offers an alternative to state‐of‐the‐art algorithms and provides advantages in terms robustness, speed, storage. One its features that it results accurate determination rotation, although lack predominant surfaces...
The calibration and refraction correction process for underwater cameras with flat-pane interfaces is presented that very easy convenient to use in real world applications while yielding accurate results. derived from an analysis of the axial camera model cameras, which among others computationally hard tackle. It shown how realistic constraints on distance window can be exploited, leads approach dubbed Pinax Model as it combines aspects a virtual pinhole projection function model. allows...
Given that 3D scan matching is such a central part of the perception pipeline for robots, thorough and large-scale investigations performance are still surprisingly few. A crucial scientific method to perform experiments can be replicated by other researchers in order compare different results. In light this fact, paper presents comparison registration algorithms using recently published benchmark protocol which makes use publicly available challenging data set covers wide range...
Underwater manipulation is a challenging problem. The state-of-the-art technology dominated by remotely operated vehicles (ROVs). ROV operations typically require an offshore crew consisting of, at minimum, intendant (or supervisor), operator, and navigator. This must often be doubled or even tripled due to work shifts. In addition, customer representatives wish physically present offshore. Furthermore, underwater intervention missions are still significant amount of lowlevel, manual control...
ISO/IEC 15504 is an emerging international standard on software process assessment. It defines a number of engineering processes and scale for measuring their capability. One the defined requirements analysis (SRA). A basic premise measurement that higher capability associated with better project performance (i.e., predictive validity). The paper describes empirical study evaluates validity SRA Assessments using were conducted 56 projects world-wide over period two years. Performance...
Software product lines can be very powerful for ensuring quality, economic efficiency, and manageability of software system families. SPLs are relevant to large industrial enterprises that want better manage their software-intensive systems' development. They also provide small start-ups with unique striking business models. However, SPL technology difficult implement maintain. A work group comprising five organizations has investigated compared practices. The results detail the state practice.
Rescue robotics is an important steppingstone in the scientific challenge to create autonomous systems. There a significant market for rescue robots, which have unique features that allow fruitful combination of application-oriented developments and basic research. Unlike other markets advanced systems like service domain benefits from fact there human loop, allows stepwise transition dumb teleoperated devices truly Current are already very useful this they benefit any bit autonomy added....
We propose a robust gesture-based communication pipeline for divers to instruct an Autonomous Underwater Vehicle (AUV) assist them in performing high-risk tasks and helping case of emergency. A gesture language (CADDIAN) is developed, based on consolidated standardized diver gestures, including alphabet, syntax semantics, ensuring logical consistency. hierarchical classification approach introduced hand recognition stereo imagery multi-descriptor aggregation specifically cope with underwater...
This paper presents a new technique for the update of probabilistic spatial occupancy grid map using forward sensor model. Unlike currently popular inverse models, models can be found experimentally and represent characteristics better. The formulation is applicable to both 2D 3D range sensors does not have some theoretical practical problems associated with current approaches which use models. As an illustration this procedure, prototype model derived beam represented as spherical sector....
Safety, security, and rescue robotics is an important application field that can be viewed as a prototypical example of domain where networked mobile robots are used for the exploration unstructured environments inaccessible to or dangerous humans. Teleoperation, based on wireless networks, much more complex than what one might expect at first glance because it goes well beyond mere mappings low-level user inputs - like joystick commands motor activations robot. Teleoperation SSRR must move...
This article discusses the scientifically and industrially important problem of automating process unloading goods from standard shipping containers. We outline some challenges barring further adoption robotic solutions to this problem, ranging handling a vast variety shapes, sizes, weights, appearances, packing arrangements goods, through hard demands on speed reliability, ensuring that fragile are not damaged. propose modular reconfigurable software framework in an attempt efficiently...
Abstract Purpose of Review This review provides an overview the current state art in Underwater Human-Robot Interaction (U-HRI), which is area that quite different from standard (HRI). due to several reasons. First all, there are particular properties water as a medium, e.g., strong attenuation radio-frequency (RF) signals or physics underwater image formation. Second, divers bound special equipment, breathing apparatus, makes, for example, speech recognition challenging, if not impossible....
Abstract Determination of individual age is one essential step in the accurate assessment fish stocks. In non-tropical environments, manual count ring-like growth patterns otoliths (ear stones) standard method. It relies on visual means and judgment thus subject to bias interpretation errors. The use automated pattern recognition based machine learning may help overcome this problem. Here, we employ two deep methods Convolutional Neural Networks (CNNs). first approach utilizes Mask R-CNN...
This article addresses fast 3D mapping by a mobile robot in predominantly planar environment. It is based on novel pose registration algorithm entirely matching features composed of plane-segments extracted from point-clouds sampled sensor. The approach has advantages terms robustness, speed and storage as compared to the voxel approaches. Unlike previous approaches, uncertainty plane parameters utilized compute computed scan-registration. illustrated creating full model multi-level testing arena.