- Bonn, Germany
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation and manipulation. The recently presented Directional Truncated Signed Distance Function (DTSDF) is an... more
Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation and manipulation. The recently presented Directional Truncated Signed Distance Function (DTSDF) is an augmentation of the regular TSDF that shows potential for more coherent maps and improved tracking performance. In this work, we present methods for rendering depth-and color images from the DTSDF, making it a true drop-in replacement for the regular TSDF in established trackers. We evaluate the algorithm on well-established datasets and observe that our method improves tracking performance and increases re-usability of mapped scenes. Furthermore, we add color integration which notably improves color-correctness at adjacent surfaces. Our novel formulation of combined ICP with frame-to-keyframe photometric error minimization further improves tracking results. Lastly, we introduce Sim(3) point-to-plane ICP for refining pose priors in a multi-sensor scenario with different scale factors.
Research Interests:
Neural radiance-density field methods have become increasingly popular for the task of novel-view rendering. Their recent extension to hash-based positional encoding ensures fast training and inference with visually pleasing results.... more
Neural radiance-density field methods have become increasingly popular for the task of novel-view rendering. Their recent extension to hash-based positional encoding ensures fast training and inference with visually pleasing results. However, density-based methods struggle with recovering accurate surface geometry. Hybrid methods alleviate this issue by optimizing the density based on an underlying SDF. However, current SDF methods are overly smooth and miss fine geometric details. In this work, we combine the strengths of these two lines of work in a novel hash-based implicit surface representation. We propose improvements to the two areas by replacing the voxel hash encoding with a permutohedral lattice which optimizes faster, especially for higher dimensions. We additionally propose a regularization scheme which is crucial for recovering high-frequency geometric detail. We evaluate our method on multiple datasets and show that we can recover geometric detail at the level of pores and wrinkles while using only RGB images for supervision. Furthermore, using sphere tracing we can render novel views at 30 fps on an RTX 3090.
Research Interests:
In this paper, we present a three-dimensional mapping system for mobile robots using laser range sensors. Our system provides sensor preprocessing, efficient local mapping for reliable obstacle perception, and allocentric mapping with... more
In this paper, we present a three-dimensional mapping system for mobile robots using laser range sensors. Our system provides sensor preprocessing, efficient local mapping for reliable obstacle perception, and allocentric mapping with real-time localization for autonomous navigation. The software is available as open-source ROS-based package and has been successfully employed on different robotic platforms, such as micro aerial vehicles and ground robots in different research projects and robot competitions. Core of our approach are local multiresolution grid maps and an efficient surfel-based registration method to aggregate measurements from consecutive laser scans. By using local multiresolution grid maps as central data structure in our system, we gain computational efficiency by having high resolution in the near vicinity of the robot and lower resolution with increasing distance. Furthermore, local multiresolution grid maps provide a probabilistic representation of the environ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Mathematics, Computer Science, Algorithms, Artificial Intelligence, Neural Networks, and 12 moreSemi-supervised Learning, Medicine, Unsupervised Learning Techniques, Multidisciplinary, Artificial Neural Networks, Deep Learning, Unsupervised Learning, Encoder, Perceptron, Computer Science Neural Networks, Linear Transformation, and multi layer perceptron
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Robotic avatar systems promise to bridge distances and reduce the need for travel. We present the updated NimbRo avatar system, winner of the $5M grand prize at the international ANA Avatar XPRIZE competition, which required participants... more
Robotic avatar systems promise to bridge distances and reduce the need for travel. We present the updated NimbRo avatar system, winner of the $5M grand prize at the international ANA Avatar XPRIZE competition, which required participants to build intuitive and immersive telepresence robots that could be operated by briefly trained operators. We describe key improvements for the finals compared to the system used in the semifinals: To operate without a power-and communications tether, we integrate a battery and a robust redundant wireless communication system. Video and audio data are compressed using low-latency HEVC and Opus codecs. We propose a new locomotion control device with tunable resistance force. To increase flexibility, the robot's upper-body height can be adjusted by the operator. We describe essential monitoring and robustness tools which enabled the success at the competition. Finally, we analyze our performance at the competition finals and discuss lessons learned.