research
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
research [2014/11/03 10:59] aamir |
research [2014/11/03 12:50] (current) aamir |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | ====== Research Overview ====== | ||
| ### | ### | ||
| In the context of human-robot interaction, it is natural to classify humans into two distinct categories, namely users and operators. Human users are those without the specific knowledge regarding the internal operations of a robot but are expected to benefit from using that robot out of the box in a complex environmental setting. On the other hand, human operators are expected to have the basic technical knowledge of a robot's sensory and motor functionalities and be able to manipulate those in order to perform human-robot collective tasks. For both human users and operators, it is essential to have a smooth and effortless interaction with large-scale multi-robot systems operating in the real-world. However, in order to study and develop methods for such human-robot interactions that involve not only complex robotic systems but also a large number of those robots in a huge environment, it becomes impractical to experiment only with real robots. The inhibiting factors include the costs to build a large number of | In the context of human-robot interaction, it is natural to classify humans into two distinct categories, namely users and operators. Human users are those without the specific knowledge regarding the internal operations of a robot but are expected to benefit from using that robot out of the box in a complex environmental setting. On the other hand, human operators are expected to have the basic technical knowledge of a robot's sensory and motor functionalities and be able to manipulate those in order to perform human-robot collective tasks. For both human users and operators, it is essential to have a smooth and effortless interaction with large-scale multi-robot systems operating in the real-world. However, in order to study and develop methods for such human-robot interactions that involve not only complex robotic systems but also a large number of those robots in a huge environment, it becomes impractical to experiment only with real robots. The inhibiting factors include the costs to build a large number of | ||
| Line 15: | Line 16: | ||
| ### | ### | ||
| - | To solve the scalability challenge our primary focus is on exploiting the properties of conditional and mutual independence of the involved variables. Using state of the art formulation methods, such as, pose graphs and Bayesian networks, we aim to address the problem of large-scale multi-robot cooperative localization, target tracking, mapping and motion planning. A kez focus of our formulation is to optimally capture the sparsity of the system in question. | + | To solve the scalability challenge our primary focus is on exploiting the properties of conditional and mutual independence of the involved variables. Using state of the art formulation methods, such as, pose graphs and Bayesian networks, we aim to address the problem of large-scale multi-robot cooperative localization, target tracking, mapping and motion planning. A key focus of our formulation is to optimally capture the sparsity of the system in question. |
| ### | ### | ||
research.1415008791.txt.gz ยท Last modified: 2014/11/03 10:59 by aamir
Page Tools
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 3.0 Unported
