Here we link open source software that has been created in the scope of the project.
This package contains implementation for plan synthesis algorithms given a finite transition system (as the agent motion model) and a Linear temporal logic formula (as the agent task). It outputs the static plan as a sequence of agent motion and action, required to fulfill the task.
More information can be found under https://people.kth.se/~mengg/software.html.
This package contains the object detection system as it has been implemented for the RECONFIG project. A DPM model gives rise to the energy function being optimized during inference and has to be learned offline beforehand. All functionality is accessible via a ROS interface.
For more information on how to install and call, please refer to the included README.md.
In this package we provide the code of our state of the art boundary detector as published by Iasonas Kokkinos under the title "Pushing the boundaries of boundary detection using deep learning" in the International Conference on Learning Representations, 2016
For image segmentation we provide the code to the paper "Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs", published on arXiv.org.