Recently, we formed Bogazici University Virtual Reality Laboratory http://buviar.boun.edu.tr/ as a joint effort by researchers from the Dept. of Mathematics and Science Education, the Dept. of Psychology, and the Dept. of Computer Engineering.
In the CoLoRs lab, we have a robot arm (UR10) with a 3-fingered gripper and a force/torque sensor in the wrist. The aim of this project is to teach this robot to prepare cappuccino. For this, the students should
Social networking platforms are widely used to influence opinions across all kinds of domains. The high volume of short messages along with the characteristics of posts makes identifying the opinions and the dynamics of opinions rather challenging.
In this project, you will develop a program to identify and track opinions on online social networks.
This project can be formulated as Cmpe491 or Cmpe492 depending on interest.
FL is a new methodology providing privacy in learning by sharing only model parameters rather than the data directly with the server. In this project, we aim to apply well-known FL techniques to wearable data collected from university students and workers and compare them with traditional ML techniques. The dataset includes activity, sleep, and stress-related information.
In this project, you are going to implement and build upon our recently proposed symbol learning method, namely DeepSym [1], and make new experiments on new domains to discover the benefits and shortcomings of the method.
Humans can interact with objects differently by using only one hand. The grippers on the robot can be used for different actions too. Via using the contact points on the objects and detecting the movements at these points. The actions should be recognized.
In robotic, simulators are a requirement for improvement of the algorithms without causing any harm, so existing robots should be transferred to asimilasyon environment. We need to use KIT Gripper with ROS + Gazebo environment with position controller. Also, existing robot should have similar inputs with the simulations. So, we need a ROS Wrapper which takes data from real robot and converts it to required ROS messages. After environment development, the system will be tested via Human - Robot cooperative game.
Training machine learning algorithms on resource-constrained mobile and wearable devices, particularly DL algorithms, is challenging and sometimes even impossible due to the limited computation power, storage, and, most importantly, the battery. TensorflowLite is a popular platform for optimizing deep learning architectures to be deployed on mobile devices. In this project, the focus is on human activity recognition with the motion sensors embedded in smartphones.