BAM days 2021

Bio:

Klaus Kefferpütz (Prof. Dr.-Ing.) is professor for measurement and control at the University of Applied Research Augsburg, Germany and head of the Cooperative Control Lab established in 2019. His research objective are algorithms for cooperative coordination, navigation and estimation in decentralized multi-agent-systems. Currently, he is working on improving the Crazyflie navigation abilities by means of cooperative navigation. Having received his Diploma and Ph.D. in nonlinear control methods for input constrained systems from the Technical University Darmstadt in 2008 and in 2012, he worked 6 years as development and systems engineer at MBDA Germany GmbH working on algorithms for guidance, control, navigation and estimation/tracking.

Thomas Izycki received his B. Eng. in Engineering in Computer Sciences from the University of Applied Research Augsburg, in 2021. Since April 2021 he is pursuing his Master of Applied Research in Engineering (MAPR) – a research project-oriented Master-program – at the Cooperative Control Lab. His project focus is on cooperative, decentralized path planning and exploration for multi-robot teams. He is working as student assistant at the Cooperative Control Lab since 2019 and his Bachelor Thesis was the integration of a configurable Zynq-7000 series system-on-chip module into a quadcopter drone for hardware-accelerated in-flight image processing.

Simon Zittenzieher received his B. Eng. in Mechanical Engineering from the University of Applied Research Augsburg, in 2021. Currently, he is studying in the Master of Mechanical Engineering program. In his Bachelor-Thesis, he focused on the development of an autonomous exploration strategy for programmable mini-quadcopters employing artificial neural networks. He will continue his work in this field as a student assistant at the Cooperative Control Lab in parallel to his Master-studies.

Christos Zosimidis received his B. Eng. in Engineering in Computer Sciences from the University of Applied Research Augsburg in 2021. Since October 2021 he is working as Embedded Software Developer at Engineering Office for Thermoacoustic (IfTA) GmbH in Puchheim, Munich. He worked as a student assistant in the Cooperative Control Lab from October 2019 to September 2021 focusing on decentralized communication strategies for the Crazyflie. In his Bachelor-Thesis, he applied this strategy for cooperative path planning for a swarm of mini-quadcopters

Bio:

Joseph is a PhD student from the Department of Media Technology and Interaction Design at KTH University Stockholm. His research is about designing small drones that can be directly manipulated by different parts of the body. This is done by making the drone respond to small changes in movement, breath and balance. Through this work he aims to investigate ways in which we come to appreciate how we move our bodies in our everyday lives.

Joseph’s personal homepage

Magnus Sjölin and Martin Holmberg are from Qualisys. The Swedish motion capture company.

Qualisys is a leading provider of precision motion capture and 3D positioning tracking system. With a +30 years-long history of supplying a variety of industries with high-end camera systems and expertise. Indoor, outdoor, ground-to-air or underwater – no matter what condition, they have your solution.

Bio:

Daniele Palossi received the Ph.D. in Information Technology and Electrical Engineering from the ETH Zürich, in 2019. He is currently a Postdoctoral Researcher at the Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland, and at the Integrated Systems Laboratory (IIS), ETH Zürich, Zürich, Switzerland. His research focuses on the embedded domain with special emphasis on energy-efficient ultra-low-power platforms, algorithms for autonomous navigation, and resource-constrained small-sized cyber-physical systems. His work has resulted in 20+ publications in international conferences and journals. Dr. Palossi was a recipient of the Swiss National Science Foundation (SNSF) Spark Grant and the 2nd prize at the Design Contest held at the ACM/IEEE ISLPED’19.

Bio:

Francesco Paci received the B.Sc. and M.Sc. degrees in computer engineering from the University of Bologna, where he also pursued the Ph.D. degree in electronics, telecommunications, and information technologies with a thesis on Electronic Systems with High Energy Efficiency for Embedded Computer Vision. He was a Visiting Student with Trinity College Dublin, a Visiting Researcher with Movidius (now Intel Movidius), Dublin, in 2014, and STMicroelectronics, Grenoble, in 2012. Since 2017 he holds a full time position at Greenwaves-Technologies as R&D software engineer.

Bio:

Wolfgang Hönig is an independent junior research group leader at TU Berlin, Germany, heading the Intelligent Multi-Robot Coordination Lab. Previously, he was a postdoctoral scholar at the California Institute of Technology, USA. He received the diploma in Computer Science from TU Dresden, Germany in 2012, and the M.S. and Ph.D. degrees from the University of Southern California (USC), USA in 2016 and 2019, respectively. His research focuses on enabling large teams of physical robots to collaboratively solve real-world tasks, using tools from informed search, optimization, and machine learning. Wolfgang has been using the Crazyflie since 2014, co-developed the Crazyswarm to fly up to 49 Crazyflies in 2016, and was a visiting research scientist at Bitcraze in 2021.

Abstract: Swarms of autonomous drones can help humans in search-and-rescue missions, in keeping track of the stock in warehouses or in monitoring crop in greenhouses. We are convinced that such complex tasks can and even should be performed by drones the size of BitCraze’s CrazyFlies. Tiny drones like the CrazyFlie are very safe for humans, suitable for flying in narrow environments, and quite cheap so that they can be produced in large numbers. However, it is also notoriously hard to make such tiny drones fly completely autonomously. Due to their extremely low weight, they are very limited in terms of energy and payload. This implies that they can carry few sensors and extremely little processing compared to, e.g., self-driving cars. In our talk, we will talk about the effort at TU Delft’s MAVLab to make swarms of tiny autonomous drones, and how we approach this by drawing inspiration from insect intelligence. We will present our work on ultra-light autonomous drones such as the 20 gram “DelFly Explorer”. Our focus will be on swarming, and on making tiny drones localize with respect to the other swarm members. We will also talk about two different studies in which swarms of Crazyflies perform incredibly complex tasks. In the first study, a swarm of CrazyFlies is able to explore an unknown environment and come back to the departure point. In the second study, a swarm of CrazyFlies is able to autonomously localize gas sources in complex environments. In our talk we argue that CrazyFlie drones will turn out to be useful far beyond motion tracking arenas.

Bio:

Guido de Croon: Received his M.Sc. and Ph.D. in the field of Artificial Intelligence (AI) at Maastricht University, the Netherlands. His research interest lies with computationally efficient, bio-inspired algorithms for robot autonomy, with an emphasis on computer vision. Since 2008 he has worked on algorithms for achieving autonomous flight with small and light-weight flying robots, such as the DelFly flapping wing MAV. In 2011-2012, he was a research fellow in the Advanced Concepts Team of the European Space Agency, where he studied topics such as optical flow based control algorithms for extraterrestrial landing scenarios. After his return at TU Delft, his work has included fully autonomous flight of a 20-gram DelFly, a new theory on active distance perception with optical flow, and a swarm of tiny drones able to explore unknown environments. Currently, he is Full Professor at TU Delft and scientific lead of the Micro Air Vehicle lab (MAVLab) of Delft University of Technology

Bio:

Bart Duisterhof received his B.Sc. and M.Sc. in Aerospace Engineering from Delft University of Technology, the Netherlands. His interests lie in efficient algorithms for robot autonomy of tiny flying machines. From 2016 to 2020 he worked with Professor Guido de Croon, first exploring visual servoing of the DelFly Nimble, a 30-gram flapping wing MAV. Later they contributed the first fully autonomous swarm of gas-seeking nano quadcopters, Sniffy Bug. In 2019 Bart was a visiting research fellow at Harvard University with Vijay Janapa Reddi, where he studied applications of deep reinforcement learning on nano drones. He is currently a Ph.D. student at Carnegie Mellon University.