MIN-Fakultät
Fachbereich Informatik
TAMS

64-476 Oberseminar Technische Aspekte Multimodaler Systeme

Procedure Zoom meeting
Schedule Tuesdays, 16:00 - 17:30
URL Meeting-ID: 977 4708 0367 Please contact the organizer for the password in case you want to participate.
Location Informatikum F-334
Organizer Jianwei Zhang

Schedule

05.04. Preliminary Discussion and Planning
Speaker all

12.04. Robot Visuo-Tactile Multimodal and Crossmodal Learning
Speaker Dr. Shan Luo (King's College London)
Abstract Abstract: In our daily life, both vision and touch are indispensable sensing methods for us to interact with the surrounding environment, and they two often assist each other to complete some tasks, such as grasping objects. Similarly, visual and tactile perception can also assist each other as the main channel for robots to understand the surrounding environment. Inspired by this, we developed a new type of touch sensor named GelTip, which is shaped like a human finger. It uses a vision camera at the bottom to capture the contact between the sensor surface elastomers and the contacting object, and extracts information about the contacting object based on the obtained tactile image. We have also designed a series of learning algorithms for extracting information from both visual and tactile images. Through the integration of vision and touch (both multi- and cross-modal), it can effectively improve the robot's object perception ability, so that the robot can effectively improve its capability of object recognition and localisation. Recently, we have also developed a simulation model of high-resolution tactile sensors that can be applied in the widely used ROS simulation environments and enables the Sim2Real learning with tactile sensing. Our research can be used to improve the dexterous manipulation of robots, suitable for warehouse robotics and automated assessments of new products in advanced manufacturing.

19.04. Knowledge based of feature engineering and FPS project
Speaker Shang-Ching Liu
Slides knowledge_graph_based_of_data_fusion_and_FPS_project.pdf 1.5MB pdf

26.04. Synthetic Aperture Radar Image Interpretation Based on Deep Learning
Speaker Di Zhang

03.05. Camera calibration using of control points / Synthetic depth dataset generation
Speaker Kaixin Bai

10.05. Elastic tactile sensor skin on double-curved surfaces for robots and wearables
Speaker Philipp Ruppel
Slides Slides 4.7MB pdf

17.05. Vision Transformer and Transformer-based Shape Completion in Grasping Evaluation
Speaker Wenkai Chen

24.05. Pentecost holiday

31.05. Reinforcement Learning Based Push and Grasp to Remove Hard-to-Grasp Objects
Speaker Hao Zhang / Aimen Shahid
Slides Slides 1.0 Mi pdf
Abstract Lorem ipsum

07.06. Magic Magnetic Table: Spatial Adjustable Haptic Feedback for Virtual and Augmented Reality
Speaker Yannick Jonetzko
Slides Slides 46 Mb pdf

14.06. Capturing Pose Data for RoboCup Humanoid Soccer using AprilTags and YOLO
Speaker Florian Schleid

21.06. Lessons Learned In Robotics and Open Source Software / Applying MoveIt and ROS in Industry
Speaker Invited Talk: Dr. Dave Coleman (PickNik Robotics)
Bibliography Dr. Dave Coleman is CEO of PickNik Robotics. PickNik is accelerating global robotics innovation through open software platforms for mobile manipulation. Before co-founding PickNik, Dave worked at Google Robotics, Open Robotics, and Willow Garage. Dave is an international advocate of open source software, robotic interoperability, and new robotics standards. His insights into robot-agnostic platforms for different morphologies, different theoretical approaches, and different end-user technical requirements give him a well-rounded understanding of the needs of powerful robotic software.

28.06. Bipedal Walking on Different Robots / Footstep Planning Using Reinforcement Learning for Humanoid Robots
Speaker Marc Bestmann
Jasper Güldenstein

05.07. tba
Speaker Yunlei Shi
Michael Görner (postponed after recent quarantine)

12.07. tba
Speaker Hongzhuo Liang
Jianzhi Lyu