Student Projects

LiDAR Inertial Odometry (LIO) has become a key technology in robotics, as it provides accurate localization and mapping through the fusion of LiDAR data with inertial measurements. Recent research [1, 2] has shown that the use of LiDAR signal strength (intensity) can further enhance localization performance. However, unlike camera images, LiDAR intensity values are strongly influenced by factors such as distance, surface reflectivity, and angle of incidence. This dependence causes inconsistent intensity values across different scanning positions, which can negatively impact the robustness of intensity-based localization methods. A recently proposed automated method for radiometric calibration [3] has demonstrated promising results in correcting these inconsistencies for high-grade Terrestrial Laser Scanning (TLS) systems. In this project, we aim to adapt and apply this radiometric calibration methodology to LiDAR sensors commonly used in robotics. By compensating for distance and incidence-angle effects, we expect to generate more consistent LiDAR intensity images. This, in turn, will improve the robustness of LIO algorithms and contribute to more accurate localization. [1] P. Pfreundschuh et al., “COIN-LIO: Complementary Intensity-Augmented LiDAR Inertial Odometry” [2] N. Khedekar et al., “PG-LIO: Photometric-Geometric fusion for Robust LiDAR-Inertial Odometry” [3] H. Laasch et al., “Automatic in-situ radiometric calibration of TLS: Compensating distance and angle of incidence effects using overlapping scans”

- Strong competencies in one of the following areas: Robotics, Computer Vision - Demonstrated programming skills in C++ or Python - Optional: Experience with point cloud data

If you're interested in the project please send a short letter of motivation, CV and transcript of record to laaschh@ethz.ch and patripfr@ethz.ch

The objective of the thesis is to develop an algorithm capable of real-time collision avoidance for drones, ensuring safe operation even in environments with other air traffic, such as airplanes, helicopters, paragliders, and similar obstacles. The tasks include selecting and evaluating existing neural networks and algorithms, or designing a custom solution tailored to our requirements. The project also involves working with a high-performance hardware setup, with support for real-time execution on an NVIDIA Jetson Orin. Avientus provides a flexible and dynamic research environment with a budget for necessary hardware, such as cameras and sensors. Students are encouraged to experiment with and choose tools, hardware, and software frameworks that best suit their approach. This thesis offers a unique opportunity to work on cutting-edge technology in a startup environment, contributing directly to the future of automated drone logistics. If you are passionate about robotics, computer vision, and real-time systems, and are excited to tackle challenges in the aviation domain, we’d love to hear from you!

- Strong competencies in computer vision & neural networks - Good knowledge in programming (Python and / or C++) - General interest in VTOL drones

Please send your CV and transcripts to info@avientus.ch and border.rowan@ucy.ac.cy