Four papers presented at IEEE IROS 2020

At this year's International Conference on Intelligent Robots and Systems (IROS 2020) the IAR-IPR was represented with a total of four papers. Due to the Corona pandemic, the conference did not take place in Las Vegas as originally planned, but virtually.

The following papers were presented by our staff:

• Lars Berscheid, Pascal Meißner and Torsten Kröger: "Self-supervised Learning for Precise Pick-and-place without Object Model"
• Jonas Kiemel, Robin Weitemeyer, Pascal Meißner and Torsten Kröger: "TrueÆdapt: Learning Smooth Online Trajectory Adaptation with Bounded Jerk, Acceleration and Velocity in Joint Space"
• David Puljiz, Franziska Krebs, Fabian Bösing and Björn Hein: "What the HoloLens Maps Is Your Workspace: Fast Mapping and Set-Up of Robot Cells Via Head Mounted Displays and Augmented Reality"
• Patrick Schlosser and Christoph Ledermann: "Using Diverse Neural Networks for Safer Human Pose Estimation: Towards Making Neural Networks Know When They Don't Know"

The papers and the corresponding video presentations are freely available at www.iros2020.org/ondemand.