Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks. This work proposes a method to incrementally build up semantic scene graphs from a 3D environment given a sequence of RGB-D frames. To this end, we aggregate PointNet features from primitive scene components by means of a graph neural network. We also propose a novel attention mechanism well suited for partial and missing graph data present in such an incremental reconstruction scenario. Although our proposed method is designed to run on submaps of the scene, we show it also transfers to entire 3D scenes. Experiments show that our approach outperforms 3D scene graph prediction methods by a large margin and its accuracy is on par with other 3D semantic and panoptic segmentation methods while running at 35Hz.

No abstract

No abstract

No abstract

This paper presents recent and ongoing hardware and software upgrades to our humanoid robot LOLA. The purpose of these modifications is to achieve dynamic multicontact locomotion, i. e., fast bipedal walking with additional hand-environment support for increased stability and robustness against unforeseen disturbances. The upper body of LOLA has been completely redesigned with an enhanced lightweight torso frame and more robust arms with additional degrees of freedom, which extend the reachable workspace. The mechanical structure of the torso is optimized for stiffness with the help of an experimental modal analysis performed on the real hardware, while the new arm topology is the result of kinematic optimization for typical use-cases in a multi-contact setting. We also propose extensive changes to our software framework, which include a complete redesign of the onboard, real-time perception and navigation module. Although the hardware upgrade is finished and the overall software design is complete, the implementation of various modules is still work in progress.