Differences
This shows you the differences between two versions of the page.
Next revision | Previous revisionNext revisionBoth sides next revision |
research:acat [2013/04/11 09:26] – created nyga | research:acat [2023/09/18 14:04] – cstoess |
---|
====ACAT - Learning and Execution of Action Categories==== | ====== ACAT ====== |
| // Learning and Execution of Action Categories // |
| |
{{:projects:acat_logo.png?200 |}} ACAT focuses on the problem how artificial systems (robots) can understand the meaning of information made for humans. For this ACAT generates a dynamic process memory by extraction and storage of action categories from human compatible sources. Action categories include the actual action-encoding but also its context (“background”) and allow for generalization (for example replacement of objects in a given action). Thus, the ACAT system uses action categories to create action sequences (plans). These plans are grounded by perception and execution, which takes place by a robot making use of the generalization properties of the stored action categories. The ultimate purpose is to equip the robot – on an ongoing basis – with abstract, functional knowledge, normally made for humans, about relations between actions and objects leading to a system which can act meaningfully. As industrially very relevant scenario, ACAT uses “instruction sheets” (manuals) made for humans and translates these into a robot-executable format. Similar to computer science, where the development of the first compilers had led to a major step forward, the main impact of ACAT is that the project develops a robot-compiler, which translates human understandable information into a robot-executable program. | The aim of ACAT is to provide artificial systems with abstract, functional knowledge about relationships between action objects from information sources made for humans. The potential of robots would be greatly expanded if they could utilize the incredible amount of knowledge available to humans. However, most of these sources of information assume common knowledge that does not need to be explicitly specified when interpreted by humans. ACAT provides robots with this type of information and generates internal knowledge about tasks by creating and storing all required action information into “action categories”. This is done by generating dynamic process memory by extracting and storing action categories from large text and image sources. |
| |
| Action categories are designed to include both action encoding and context information obtained by combining linguistic analysis with indepth exploration and action simulation. The strength of action categories is that the rich contextual information allows for generalization (for example replacing objects in an action) and addresses ambiguity and incompleteness in planning. |
| |
| {{ projects:acat:ralph_pipetting.png?500 }} |
| |
| An example industrial application for ACAT would be to use manuals made for human workers to create instructions executable by robots. This would enable the robot to do certain human tasks without time-consuming programming procedures. The result of the ACAT project is a robot compiler which translates human-understandable information into a program that a robot can execute. |
| |
| Our role within the project is to build an action verb-specific knowledge base using first-order statistical representation, learning and reasoning, and creates an ontology of action categories. We will also coordinate the planning and execution module of the project and design and implement extensions to the Cognitive Robot Abstract Machine ([[:research:cram|CRAM]]) for concurrent reactive plan execution. |
| |
| Further information and news can be found at www.acat-project.eu |
| |
| |
| Partners: |
| | [[http://www.uni-goettingen.de/|{{:projects:acat:logos:uglogo.jpg?300}}]] | [[http://www.sdu.dk/en/|{{:projects:acat:logos:sdulogo.png?100}}]] | [[http://www.en.aau.dk/|{{:projects:acat:logos:aaulogo.png?100}}]] | |
| |
| | [[http://ai.uni-bremen.de/|{{:research:UniBremen.png?200}}]] | [[http://www.vdu.lt/en/|{{:projects:acat:logos:vdulogo.png?100}}]] | [[http://www.ijs.si/ijsw/JSI/|{{:projects:acat:logos:stefan.jpg?100}}]] | |
Prof. Dr. hc. Michael Beetz PhD
Head of Institute
Contact via
Andrea Cowley
assistant to Prof. Beetz
ai-office@cs.uni-bremen.de
Discover our VRB for innovative and interactive research
Memberships and associations:
Social Media: