robots being aware of what they are doing, how to accomplish their goals and why
The collaborative research center Everyday Activity Science and Engineering
(EASE) is an interdisciplinary research initiative at the University of Bremen that attempts to advance our understanding of how human-scale manipulation tasks can be mastered
by robotic agents. The challenge is that the same task needs to be executed by the robot in different ways depending on, for example, what tools are available, and how the environment is shaped. The key to solve this issue is generalization
. However, the robot needs to know more then what
step it needs to execute next -- it further needs to decide on how
the next step is carried out through motions
of its body, and interactions
with its environment. SOMA is an ontological model, developped in CRC EASE, that attempts to equip robotic agents with abstract knowledge to enable them performing activities in a more flexible and robust manner. The main focus of SOMA is the characterization of physical and social activity context, as well as the motions carried out by agents, and the interactions caused by them.
Take a look at SOMA releases, download released artifacts, or directly load them into an online evaluation or visualization tool for ontologies.
Please select one of the releases below.
Metrics quantify certain characteristics of an ontology such as its readability, adapatability, or reusability.
This is useful to compare different ontologies with each other, but it may also serve as quality control during development.
SOMA metrics are automatically computed by OntoMetrics
, a webservice for ontology evaluation that supports several different metrics.
For more information about the computed metrics, please visit the OntoMetrics wiki
The results of this computation for the latest SOMA version is displayed below.