Embedded Vision Systems Group

Prof Marek Gorgoń
Research and teaching professor
Head of the Group
mago@agh.edu.pl

Welcome to the Embedded Vision Systems Group.

We are part of the Computer Vision Laboratory, Department of Automatic Control and Robotics, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering (EAIiIB), AGH University of Krakow, Poland.

We conduct research on the design and implementation of embedded vision systems capable of real-time operation for high-resolution video streams (up to UHD - 3840 × 2160 @ 60 fps), while maintaining low power consumption. Our work targets autonomous flying platforms (drones, UAVs), ground vehicles and mobile robots, as well as legged and walking robotic systems, where fast and efficient perception is critical for control and decision-making.

As hardware platforms, we use reprogrammable FPGAs (Field Programmable Gate Arrays), reprogrammable SoCs (System on Chip) such as Zynq SoC and Zynq UltraScale+ MPSoC (Multi-Processor System on Chip), as well as embedded GPU solutions, including NVIDIA Jetson platforms. We are also actively exploring neuromorphic and event-based vision platforms for next-generation autonomous systems.

Featured publications

SPA
Preludium

Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs

Hubert Szolc, Karol Desnos, and Tomasz Kryjak

In 2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) , Sep 2024

Awarded Abstract DOI arXiv Bib Code Poster Website

Best Paper Award

Deep reinforcement learning (DRL) is currently the most popular AI-based approach to autonomous vehicle control. An agent, trained for this purpose in simulation, can interact with the real environment with a human-level performance. Despite very good results in terms of selected metrics, this approach has some significant drawbacks: high computational requirements and low explainability. Because of that, a DRL-based agent cannot be used in some control tasks, especially when safety is the key issue. Therefore we propose to use Tangled Program Graphs (TPGs) as an alternative for deep reinforcement learning in control-related tasks. In this approach, input signals are processed by simple programs that are combined in a graph structure. As a result, TPGs are less computationally demanding and their actions can be explained based on the graph structure. In this paper, we present our studies on the use of TPGs as an alternative for DRL in control-related tasks. In particular, we consider the problem of navigating an unmanned aerial vehicle (UAV) through the unknown environment based solely on the onboard LiDAR sensor. The results of our work show promising prospects for the use of TPGs in control related-tasks.
@inproceedings{10715635, author = {Szolc, Hubert and Desnos, Karol and Kryjak, Tomasz}, booktitle = {2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)}, title = {Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs}, year = {2024}, volume = {}, number = {}, pages = {36--41}, keywords = {Measurement;Laser radar;Navigation;Signal processing algorithms;Process control;Computer architecture;Deep reinforcement learning;Autonomous aerial vehicles;Safety;Tangled Program Graphs;TPG;Deep Reinforcement Learning;DRL;control algorithms;unmanned aerial vehicle;UAV}, doi = {10.23919/SPA61993.2024.10715635}, issn = {2326-0319}, month = sep, projects = {Preludium}, acronym = {SPA}, }