Lukas was born in Czech Republic, raised in Japan and Hong Kong, studied in Philadelphia and worked on four different continents, making him a true global citizen. He graduated from the University of Pennsylvania with a degree in Finance from the Wharton School of Business and a degree in Computer Science with a Math minor from the School of Engineering and Applied Sciences.
Lukas worked as a robotics researcher at Penn’s General Robotics, Automation, Sensing & Perception (GRASP) Lab, developing guidance, navigation and control systems for UAVs. His work resulted in multiple published papers and a patent. Lukas also got to deep-dive into machine learning at Amazon Alexa, where he developed software for the Echo Show and Echo Look.
From 2017 to 2020, Lukas worked as an Engagement Manager at McKinsey & Company, serving clients in North America, Europe, South East Asia and the Caribbean across a wide range of industries. Lukas' specialty while at the Firm were strategy, corporate finance, private equity and large-scale, rapid corporate transformations projects.
In 2020, Lukas left the Firm to return to the world of technology, working on a startup and pursuing a Masters of Robotics. In his free time, he likes to fly planes (real ones & radio-controlled), sail and ski.
Download my resumé.
Masters of Science in Engineering (Robotics), In progress
School of Engineering, University of Pennsylvania
Bachelor of Science in Economics (Finance), 2017
Wharton School of Business, University of Pennsylvania
Bachelor of Science in Engineering (Comp. Science), 2017
School of Engineering, University of Pennsylvania
May not be exhaustive, for most recent work experience please contact me.
Sample projects include:
This paper describes the solution proposed by Penn Aerial Robotics and GRASP Lab from the University of Pennsylvania at the 2016 NSF Student UAV challenge. The paper proposes a solution for the autonomous deployment and retrieval of mosquito traps in the field. These mosquito traps are used to collect mosquito samples and aid research in dangerous diseases such as yellow fever and dengue fever. Our proposed solution provides a fully autonomous mechanism for completing this mission. The major challenges encountered include detecting and docking with the trap in different outdoor lighting conditions.
Multirotor Unmanned Aerial Vehicles (UAV) have grown in popularity for research and education, overcoming challenges associated with fixed wing and ground robots. Unfortunately, extensive physical testing can be expensive and time consuming because of short flight times due to battery constraints and safety precautions. Simulation tools offer a low barrier to entry and enable testing and validation before field trials. However, most of the well-known simulators today have a high barrier to entry due to the need for powerful computers and the time required for initial set up. In this paper, we present OpenUAV, an open source test bed for UAV education and research that overcomes these barriers. We leverage the Containers as a Service (CaaS) technology to enable students and researchers carry out simulations on the cloud. We have based our framework on open-source tools including ROS, Gazebo, Docker, PX4, and Ansible, we designed the simulation framework so that it has no special hardware requirements. Two use-cases are presented. First, we show how a UAV can navigate around obstacles, and second, we test a multi-UAV swarm formation algorithm. To our knowledge, this is the first open-source, cloud-enabled testbed for UAVs.
More sample projects will be added in due time
Available for project-based work