Lidar and Visual Mapping and SLAM for Mobile Ground Robots
The first part of this talk will give an overview of a number of recent achievements of the Mobile Autonomous Robotic System (MARS) group of Prof. Schwertfeger. Research on Topological Map Representation, Lidar reflection detection and 3D point cloud semantic segmentation will be shortly presented as well as some recent advances on autonomous contro.
The emphasis of the second part of the talk is then on algorithms using monocular cameras for visual odometry and Simultaneous Localization and Mapping (SLAM). Our recent IROS paper "Pose Estimation for Omni-directional Cameras using Sinusoid Fitting" will be presented in more detail. There, we propose a novel pose estimation method for geometric vision of omnidirectional cameras. On the basis of the regularity of the pixel movement after camera pose changes, we formulate and prove the sinusoidal relationship between pixels movement and camera motion. We use the improved Fourier-Mellin invariant (iFMI) algorithm to find the motionn of pixels, which was shown to be more accurate and robust than the feature-based methods, While iFMI works only on pin-hole model images and estimates 4 parameters (x, y, yaw, scaling), our method works on panoramic images and estimates the full 6 DoF 3D transform, up to an unknown scale factor. For that we fit the motion of the pixels in the panoramic images, as determined by IFMI, to two sinusoidal functions. The offsets, amplitudes and phase-shifts of the two functions then represent the 3D rotation and translation of the camera between the two images. We perform experiments for 3D rotation, which show that our algorithm outperforms the feature-based methods in accuracy and robustness.
Bio: Since 2014 Sören Schwertfeger is an Assistant Professor at Shanghai University. He graduated with a Diploma (German equivalent of the Master) in Computer Science in 2005 from the University of Bremen, Germany. In 2012 he received this Ph.D. in Computer Science from the Jacobs Univsity Bremen. Between 2012 and 2014 he was a postdoctoral researcher at the Robotics Group of Prof. Andreas Birk at the Jacobs University Bremen. In 2010 Dr. Schwertfeger was a guest researcher at the National Institute of Standards and Technology (NIST) in Gaithersburg, Maryland, USA, and in 2015 he spent two months as a visiting researcher at University of California, Berkeley, USA.
His research interest is in robotics, especially intelligent functions for mobile robots. Besides his work on mapping and SLAM, Dr. Schwertfeger is working on mobile manipulation and rescue robotics, object detection and robot autonomy. Sören Schwertfeger was the general chair of the 2017 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR). He is a RoboCup Executive, an associate editor of the the IEEE Robotics and Automation Magazine and recently published, as a guest editor, a special issue on SSRR in the Journal of Field Robotics.
Zeit & Ort
24.01.2020 | 14:00 c.t. - 16:00
Takustr. 9, SR006