Personal tools
You are here: Home Projects Violet
« February 2018 »
Log in

Forgot your password?


Visual Interpreter and Modeller for Objects and Relations

Violet (Visual interpreter and modeller for objects and relations) is a visual world modeling system for autonomous manipulation robots to represent their worlds.


Service robots need to handle a variety of everyday manipulation tasks to accomplish household chores such as cooking and cleaning. Successful execution of these tasks is highly dependent on how reliable the robot perceives its environment through noisy sensing. We present Violet as a visual world modeling system for service robots to generate and maintain accurate models of their environments for continuous scenarios. This system is designed to provide a generic platform for both humanoid and ground manipulation robots using  different types of vision sensors and algorithms. In our particular implementation, data processed by different perception algorithms relying on visual sensors are used for building and continuously updating a world model about the robot's environment. We evaluate our system on a variety of object manipulation scenarios and show that the system produces consistent perception outcomes suitable for different types of manipulation tasks.


Article can be accessed here.

The source code and rosbag files are available now. 

Supplementary videos for the Baxter robot and the ground robot are available.


Document Actions