A5004109591- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- Advanced Optical Sensing Technologies
- Robot Manipulation and Learning
- Remote Sensing and LiDAR Applications
- 3D Surveying and Cultural Heritage
- Advanced Vision and Imaging
- Modular Robots and Swarm Intelligence
- Robotics and Automated Systems
- Optical measurement and interference techniques
- Indoor and Outdoor Localization Technologies
- Robotic Locomotion and Control
- Video Surveillance and Tracking Methods
- Hand Gesture Recognition Systems
- Soft Robotics and Applications
- UAV Applications and Optimization
- Gaze Tracking and Assistive Technology
- Human Pose and Action Recognition
- Advanced Image and Video Retrieval Techniques
- Prosthetics and Rehabilitation Robotics
- Autonomous Vehicle Technology and Safety
- Multimodal Machine Learning Applications
- Gait Recognition and Analysis
- Teleoperation and Haptic Systems
University of Bonn
2010-2019
Czech Academy of Sciences, Institute of Computer Science
2011
Fraunhofer Institute for Intelligent Analysis and Information Systems
2009
Robots that solve complex tasks in environments too dangerous for humans to enter are desperately needed, e.g., search and rescue applications. We describe our mobile manipulation robot Momaro, with which we participated successfully the DARPA Robotics Challenge. It features a unique locomotion design four legs ending steerable wheels, allows it both drive omnidirectionally step over obstacles or climb. Furthermore, present advanced communication teleoperation approaches, include immersive...
The past years have shown a remarkable growth in use-cases for micro aerial vehicles (MAVs). Conceivable indoor applications require highly robust environment perception, fast reaction to changing situations, and stable navigation, but reliable sources of absolute positioning like GNSS or compass measurements are unavailable during flights. We present high-performance autonomous inventory MAV operation inside warehouses. navigates along warehouse aisles detects the placed stock shelves...
Modern 3D laser-range scanners have a high data rate, making online simultaneous localization and mapping (SLAM) computationally challenging. Recursive state estimation techniques are efficient but commit to estimate immediately after new scan is made, which may lead misalignments of measurements. We present SLAM approach that allows for refining alignments during mapping. Our method based on local hierarchical optimization back-end. Measurements laser scanner aggregated in multiresolution...
Abstract This article investigates the use of time‐of‐flight (ToF) cameras in mapping tasks for autonomous mobile robots, particular simultaneous localization and (SLAM) tasks. Although ToF are principle an attractive type sensor three‐dimensional (3D) owing to their high rate frames 3D data, two features make them difficult as sensors, namely, restricted field view influences on quality range measurements by dynamics object reflectivity; addition, currently available models suffer from poor...
Grasping individual objects from an unordered pile in a box has been investigated static scenarios so far. In this paper, we demonstrate bin picking with anthropomorphic mobile robot. To end, extend global navigation techniques by precise local alignment transport box. Objects are detected range images using shape primitive-based approach. Our approach learns object models single scans and employs active perception to cope severe occlusions. Grasps arm motions planned efficient...
Time-of-flight cameras constitute a smart and fast technology for 3D perception but lack in measurement precision robustness. The authors present comprehensive approach environment mapping based on this technology. Imprecision of depth measurements are properly handled by calibration application several filters. Robust registration is performed novel extension to the Iterative Closest Point algorithm. Remaining errors reduced global relaxation after loop-closure surface smoothing. A...
Pointing gestures are a common and intuitive way to draw somebody's attention certain object. While humans can easily interpret robot gestures, the perception of human behavior using sensors is more difficult.
Micro aerial vehicles (MAV) pose a challenge in designing sensory systems and algorithms due to their size weight constraints limited computing power. We present an efficient 3D multi-resolution map that we use aggregate measurements from lightweight continuously rotating laser scanner. estimate the robot's motion by means of visual odometry scan registration, aligning consecutive scans with incrementally built map. By using local multi-resolution, gain computational efficiency having high...
Micro aerial vehicles, such as multirotors, are particularly well suited for the autonomous monitoring, inspection, and surveillance of buildings, e.g., maintenance or disaster management. Key prerequisites fully operation micro vehicles real‐time obstacle detection planning collision‐free trajectories. In this article, we propose a complete system with multimodal sensor setup omnidirectional perception consisting three‐dimensional (3D) laser scanner, two stereo camera pairs, ultrasonic...
Mobile manipulation tasks are one of the key challenges in field search and rescue (SAR) robotics requiring robots with flexible locomotion abilities. Since mostly unknown advance, robot has to adapt a wide variety terrains workspaces during mission. The centaur-like Centauro hybrid legged-wheeled base an anthropomorphic upper body carry out complex environments too dangerous for humans. Due its high number degrees freedom, controlling direct teleoperation approaches is challenging...
Time-of-Flight (ToF) cameras gain depth information by emitting amplitude-modulated near-infrared light and measuring the phase shift between emitted reflected signal. The is proportional to object's distance modulo wavelength of modulation frequency. This results in a ambiguity. Distances larger than are wrapped into sensor's non-ambiguity range cause spurious measurements. We apply Phase Unwrapping reconstruct these Our approach based on probabilistic graphical model. use loopy belief...
Reliably perceiving obstacles and avoiding collisions is key for the fully autonomous application of micro aerial vehicles (MAVs), Limiting factors increasing autonomy complexity MAVs are limited onboard sensing processing power. In this paper, we propose a complete system with multimodal sensor setup omnidirectional obstacle perception. We developed lightweight 3D laser scanner visual detection using wide-angle stereo cameras. Detected aggregated in egocentric grid maps. implemented fast...
Obstacle detection and real-time planning of collision-free trajectories are key for the fully autonomous operation micro aerial vehicles in restricted environments. In this paper, we propose a complete system with multimodal sensor setup omnidirectional obstacle perception consisting 3D laser scanner, two stereo camera pairs, ultrasonic distance sensors. Detected obstacles aggregated egocentric local multiresolution grid maps. We generate multi-layered approach: from mission to global...
Joint attention between a human user and robot is essential for effective human-robot interaction. In this work, we propose an approach to person awareness the perception of showing pointing gestures domestic service robot. contrast previous do not require be at predefined position, but instead actively orient towards communication partner. For perceiving estimating direction Time-of-Flight camera used. Estimated directions shown objects are matched in robot's environment. Both as well...
The registration of 3D laser scans is an important task in mapping applications. For the with autonomous micro aerial vehicles (MAVs), we have developed a light-weight scanner. Since scanner rotated quickly for fast omnidirectional obstacle perception, acquired point clouds are particularly sparse and becomes challenging. In this paper, present thorough experimental evaluation algorithms order to determine applicability both algorithms. Using estimated poses MAV, aim at building local...
Solving mobile manipulation tasks in inaccessible and dangerous environments is an important application of robots to support humans. Example domains are construction maintenance manned unmanned stations on the moon other planets. Suitable platforms require flexible robust hardware, a locomotion approach that allows for navigating wide variety terrains, dexterous capabilities, respective user interfaces. We present CENTAURO system which has been designed these requirements consists Centauro...
Planetary exploration scenarios illustrate the need for autonomous robots that are capable to operate in unknown environments without direct human interaction. At DARPA Robotics Challenge, we demonstrated our Centaur-like mobile manipulation robot Momaro can solve complex tasks when teleoperated. Motivated by DLR SpaceBot Cup 2015, where should explore a Mars-like environment, find and transport objects, take soil sample, perform assembly tasks, developed capabilities Momaro. Our perceives...