DLR - Institute of Robotics and Mechatronics

Home|Sitemap|Contact|Accessibility Imprint and terms of use Privacy Cookies & Tracking |Deutsch

You are here: Home:Publications and downloads:Software

Software

Stable Baselines3

Stable Baselines3 provides reliable open-source implementations of deep reinforcement learning (RL) algorithms in Python.

Augmented Autoencoders

Augmented Autoencoders (AAEs) are an approach developed at the institute to train neural networks for object pose estimation on synthetically rendered images from 3D models.

DLR CalDe and DLR CalLab - Camera Calibration Software

"DLR CalDe and DLR CalLab" is a camera calibration toolbox that implements the well-known method of Zhang, Sturm and Maybank. The toolbox consists of two independent software components: While DLR CalDe detects corner features on the calibration pattern, DLR CalLab addresses the optimal estimation of the camera parameters.

Screenshot of RAFCON with an example state machine

RAFCON: visual state machine programming

RAFCON is a tool for visual programming of hierarchical state machines. It is intended for the coordination of the task-flow of complex robotic systems, e.g. for mission control. Its feature-rich GUI and sophisticated debugging mechanisms permit fast prototyping and intuitive task development.

cvkit

The cvkit software package is offered for supporting an easy exchange and analysis of computer vision data including images in floating point format and 3D data like point clouds or triangle meshes. The toolkit targets researchers as well as interested groups and individuals. It is also especially useful for working with the Middlebury stereo and multi-view data.