Where is my stuff?

The task is to program a mobile robot to generate a map of the environment, and detect and mark objects of interest in it. Afterwards, you should plan and execute a path to go through all object location, detect whether they are still there, and report back the results.

Solving tangram puzzles

The goal of the project is to generate and assemble tangram puzzles [1] using a robotic arm with a 2-finger or suction gripper. The input for the generation is an image and the assembly sequence has to be determined to ensure a successful assembly execution.

[1] https://en.wikipedia.org/wiki/Tangram

Autonomous racing

The task is to learn a reinforcement learning agent to autonomously drive through a given race track. For simulation training we use the pybullet simulation given in [1]. After successfully training the agent, we deploy it on a real F1/tenth cart and drive a track in the hallway of our building.

[1] https://github.com/gonultasbu/racecar_gym-1

Find the viewpoint!

The task is to find the viewpoint of the given RGB image within the context of an eye-in-hand tabletop configuration.

Rock, paper, scissors

The task is to implement a version of Rock Paper Scissors on our 5-finger Psyonic hand [1].

[1] https://www.psyonic.io/ability-hand

Social force model for crowd simulation

The task is to implement social force model (SFM) for crowd simulation and visualize it in a 3D environment.

Manipulation with a quadruped robot

The project aims to develop an autonomous quadruped robotics system capable of performing mapping, navigation, object detection and manipulation.

Learning-based navigation among dynamic obstacles

Using state-of-the-art deep reinforcement learning methods, you will teach a robot to navigate among static and dynamic obstacles. Here, a neural network is trained that directly controls the robot based on observations through a LIDAR sensor. You will design your own learning architecture that includes the network design for a solid understanding of the for the robot partially observable environment, and the reward function for informative and efficient learning of the navigation objectives. After the robot successfully has trained in Pybullet-based simulation, the goal is to transfer the policy onto a real robot using ROS.

Collaborative stacking and sorting system with mobile robots

In this project, students will develop a collaborative system using two TurtleBots for stacking and sorting items. The first TurtleBot has to collect cubes and balls and stack them at the first station, while the second TurtleBot has to sort the stacked items by color into different stations.