Violet (Visual Interpreter and Modeller for Objects and Relations)

Summary:

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.

Publications:

Continuous Visual World Modeling for Autonomous Robot Manipulation
Arda Inceoglu, Cagatay Koc, Besim Ongun Kanat, Mustafa Ersen, Sanem Sariel,
IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018
[Source Code] [Data]

ToRK 2018 Eğitimi için tıklayınız.

We would like to thank Gokhan Solak for his great logo design.