Importance of Shape Features, Color Constancy, Similarity Measures in Open-Ended Object Recognition

To show the strength of the proposed approach, we carried out a real-robot experiment in the context of the serve_a_coke scenario. Towards this goal, we have integrated the proposed approach into the cognitive robotics system presented in [1]. In this experiment, a table is in front of a Kinect sensor, and a user interacts with the system. There are instances of four object categories on the table: CokeCan, BeerCan, Cup, and Vase. This is a suitable set of objects for this test since there are objects with very similar shapes and different colors (CokeCan, BeerCan, and Cup) and also objects with very different shapes and similar colors (CokeCan and Vase).
At the start of the experiment, the set of categories known to the system is empty, and therefore, the system recognizes all table-top objects as Unknown. A user interacts with the system by teaching all object categories. The system conceptualizes them using the extracted object views and recognizes all objects properly. In this task, the robot must be able to detect the pose of objects as well as recognize the label of all active objects. Afterward, it has to grasp the CokeCan object and transport it on top of the Cup object and serve the drink. This evaluation illustrates the process of learning object categories in an open-ended fashion.
If you are interested to read more about this work, please check our paper at: arxiv.org/abs/...
[1] . H. Kasaei, N. Shafii, L. Seabra Lopes, and A. M. Tome, “Interactiveopen-ended object, affordance, and grasp learning for robotic manipulation,” IEEE/RSJ International Conference on Robotics andAutomation (ICRA 2019). pp. 3747-3753.