| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| download [2013/01/02 16:03] – [Simple dialog system] tenorth | download [2013/04/22 08:25] (current) – admin |
|---|
| ====== KnowRob installation ====== | #REDIRECT installation |
| ~~NOTOC~~ | |
| KnowRob is available as part of the [[http://www.ros.org/|ROS robot middleware]] and has been part of the official ROS distribution since ROS Diamondback. There are pre-built .deb packages for Ubuntu in the ROS repository. If you are using another platform or would like to modify the system, you can install KnowRob from source. | |
| | |
| Ubuntu Linux is the only supported platform, though other Linux distributions should work without problems. In principle, installation in MacOS and Windows should also be possible (at least all dependencies are available), but there is no support. If you succeed in installing the system on one of these platforms, please notify the KnowRob developers. | |
| | |
| ===== Installation from binary packages ===== | |
| After adding the ROS repository to your sources.list as described [[http://www.ros.org/wiki/fuerte/Installation/Ubuntu|here]], you can install KnowRob using | |
| <code> | |
| sudo apt-get install ros-fuerte-knowrob | |
| </code> | |
| For future releases, replace 'fuerte' with the respective distribution code name (e.g. 'groovy'). All dependencies are automatically resolved and installed by the Ubuntu package manager. | |
| | |
| | |
| ===== Installation from source ===== | |
| | |
| You can check out the KnowRob source code using | |
| <code> | |
| svn co http://code.in.tum.de/pubsvn/knowrob/tags/latest knowrob | |
| </code> | |
| You will need to set up your local ROS workspace as described [[http://www.ros.org/wiki/ROS/Tutorials/InstallingandConfiguringROSEnvironment|here]]. The workspace should contain your KnowRob folder -- you can test if your installation is correct by typing ''roscd knowrob'' in a terminal, which should jump into the KnowRob folder. | |
| | |
| ==== Install dependencies ==== | |
| | |
| KnowRob depends on other ROS stacks as well as system libraries. Besides more common ROS stacks, KnowRob depends on the stack //ias_common//. Please check it out into your ROS workspace using the following command: | |
| <code> | |
| git clone http://code.in.tum.de/git/ias-common.git ias_common | |
| </code> | |
| | |
| For Ubuntu, the //ias_common// stack is also available as .deb package. Further dependencies can be resolved using [[http://www.ros.org/wiki/rosdep|rosdep]] (for system dependencies) and [[http://www.ros.org/wiki/roslocate|roslocate]] (for dependencies on other ROS packages). If there are no rosdep rules for your platform, have a look at the rosdep.yaml file in the knowrob folder to see a list of programs that need to be installed. | |
| | |
| ==== Compile the system ==== | |
| If your ROS workspace is set up correctly (as you have verified with the //roscd// command) and if you have all dependencies installed, you can compile knowrob using the //rosmake// tool: | |
| <code> | |
| rosmake knowrob | |
| </code> | |
| | |
| ====== Related tools and packages ====== | |
| | |
| ==== CRAM ==== | |
| The [[http://www.ros.org/wiki/cram_core|Cognitive Robot Abstract Machine (CRAM)]] is a software toolbox for the design, the implementation, and the deployment of cognition-enabled autonomous robots performing everyday manipulation activities. KnowRob is used as knowledge base that provides the robot executive with question-answering capabilities. | |
| | |
| ==== RoboEarth ==== | |
| [[http://www.ros.org/wiki/roboearth|RoboEarth]] is a European research project that investigates how robots can exchange knowledge via a web-based platform, similar to the way humans exchange knowledge via Wikipedia. KnowRob serves as local knowledge base on the robots, and representations from KnowRob are used for describing the exchanged information. | |
| | |
| ==== ProbCog: statistical relational learning library ==== | |
| | |
| [[http://wwwbeetz.informatik.tu-muenchen.de/probcog-wiki|ProbCog]] is a statistical relational learning and reasoning system that supports efficient learning and inference in relational domains. It provides an extensive set of open-source tools for both undirected and directed statistical relational models. ProbCog can read evidence from KnowRob, and can be called from KnowRob via Prolog predicates. Have a look at the [[http://www.ros.org/wiki/mod_probcog|mod_probcog]] package for details on the interface. | |
| | |
| | |
| | |
| | |
| ==== Semantic Map editor ==== | |
| This [[http://www.ros.org/wiki/mod_semantic_map|graphical editor]] facilitates the creation and modification of semantic maps. Users can easily create, delete and modify object instances. | |
| | |
| ==== Import of natural-language Web instructions ==== | |
| The package [[http://www.ros.org/wiki/comp_ehow|comp_ehow]] provides methods for converting natural-language task instructions into the format used in KnowRob. It employs a combination of statistical parsing, disambiguation and ontological concept resolution. | |
| | |
| ==== Simple dialog system ==== | |
| The [[http://tum-ros-pkg.svn.sourceforge.net/viewvc/tum-ros-pkg/knowledge/mod_dialog|mod_dialog]] package realizes a simple dialog system that allows interaction with the knowledge base using simplified natural language. Each question type is handled by a Java class that translates a natural-language string into a Prolog query and generates some natural-language output from the result. The package further contains a simple speech recognition node implemented using the [[http://cmusphinx.sourceforge.net|Sphinx speech recognizer]]. | |
| | |
| ==== Labeling tool for human activities ==== | |
| This [[https://github.com/knowrob/data_labeling_tool|GUI program]] facilitates the annotation of observations of human actions. It can load videos and sequences as still images and offers different options for creating annotations. As output, it can generate different annotation file formats that describe what the observed subject is doing. | |
