Navigation und Umweltrobotik: Pedestrian Navigation – Obstacle Avoidance with Depth Cameras and Electrical Muscle Stimulation
This is a topic offered by the Human-Computer Interaction Group.
In previous projects the Human-Computer Interaction Group investigated a novel approach to control pedestrians' walking direction for navigation. We showed that controlling the direction with electrical muscle stimulation is possible in outdoornavigation scenarios. As a follow-up project we would like to explore - in a collaborative project with the Institute of Cartography and Geoinformatics (IKG) - how this approach can be used for obstacle avoidance in pedestrian navigation scenarios.
In this follow-up project we plan to investigate vision-based obstacle detection with depthcameras (e.g. Kinect 2 or stereo cameras) to create 3D point clouds. Features of the ROS(Robot Operating System) should be used to design and develop a navigation prototype that detects obstacles and steers a user around them. The prototype is going to be tested in outdoor navigation studies. You will get a deeper understanding of novel hapticfeedback methods, depth sensors, navigation algorithmic, mobile development,prototyping, and user study design.
This thesis consists of the following work packages:
- Understanding depth sensors and generating 3 D point clouds
- Generating local maps based on point clouds
Actuated navigation with electrical muscle stimulation (EMS)
- Understanding of a novel navigation approach using EMS
- Implementing controller software for actuated navigation
- Collision avoidance using the ROS navigation stack (path planning)
- Designing and conducting a user study
- Analyzing the results
You should ideally have knowledge in C/C++, Android, and Linux development. If you are interested in new haptic feedback methods, depth sensors, navigation, prototyping, and user study design, please contact Steffen Busch (Email: Steffen.Busch@ikg.uni-hannover.de, Tel: 762-3726) or Max Pfeiffer (Email: firstname.lastname@example.org, Tel: 762-14153)
Contact: Steffen Busch