Enabling Technologies for Personal Aerial Transportation Systems

Mycopter is a new project funded by the European Union under the 7th Framework Programme to investigate enabling technologies for a personal aerial transportation system (PATS). More information can be found on the official project website.

Lifting public transportation into the third dimension

A concept cockpit

Considering the prevailing congestion problems with ground-based transportation and the anticipated growth of traffic in the coming decades, a major challenge is to find solutions that combine the best of ground-based and air-based transportation. The optimal solution would consist of  creating a personal air transport system (PATS) that can overcome the environmental and financial costs associated with all of our current methods of transport.
We propose an integrated approach to enable the first viable PATS based on Personal Aerial Vehicles (PAVs) envisioned for travelling between homes and work places, and for flying at low altitudes in urban environments. Such PAVs should be fully or partially autonomous without requiring ground-based air traffic control. Furthermore, they should operate outside controlled airspace while current air traffic remains unchanged, and should later be integrated into the next generation of controlled airspace.

The myCopter project aims to pave the way for PAVs to be used by the general public within the context of such a transport system. The project consortium consists of experts that can make the technology advancements necessary for a viable PATS, and a partner to assess the impact of the envisioned PATS on society (socio-technological evaluation). To this end, test models of handling dynamics for potential PAVs will be designed and implemented on unmanned aerial vehicles, motion simulators, and a manned helicopter. In addition, an investigation into the human capability of flying a PAV will be conducted, resulting in a user-centred design of a suitable human-machine interface (HMI).

A concept Personal Aerial Vehicle

Furthermore, the project will introduce new automation technologies for obstacle avoidance, path planning and formation flying, which also have excellent potential for other aerospace applications. This project is a unique integration of technological advancements and social investigations that are necessary to move public transportation into the third dimension.

Research topics at EPFL
The research components carried out at EPFL concern collision avoidance systems for PAVs. Current air traffic control and regulations are designed for low traffic densities (average airplane separation is tens of kilometers). In a future personal air transport system, traffic densities would be much higher, with dozens of vehicles per cubic kilometer. This means that current systems for controlled airspace that rely on centralised control and voice communication between a controller and the pilots will not be able to deal with this situation. Regulations for uncontrolled airspace mostly rely on the pilot performing visual collision avoidance – this can be a challenging task in high density traffic, and potentially beyond the capabilities of the average user.

Our task is to identify sensor systems that can detect multiple aircrafts reliably, either collaboratively (by automatic communication with nearby PAVs) or non-collaboratively (detecting aircrafts and other obstacles that do not carry a compatible collision avoidance system). Potential sensor modalities are based on GPS, radio communication, radar, acoustics, and electro-optical systems including laser sensors and computer vision. EPFL’s CVLab collaborates on computer vision techniques for detecting other aircrafts, and identifying obstacle-free landing locations. We will develop a small-scale sensor suite and test it on autonomous robotic aircrafts. This research has obvious potential benefits in the near future for Unmanned Aerial Vehicles (UAVs) and the currently available, lightweight personal aircrafts.

A further research topic is collaborative navigation and flightpath planning to reduce the overall risk of collisions and provide efficient traffic flow for large numbers of PAVs. We will investigate the feasibility of various decentralised control strategies, possibly seeking inspiration from nature (such as flocking birds). The goal is to group PAVs travelling in similar directions and separate them from traffic moving in different directions.
Pendul’Air: a concept for a PAV

Pendul'Air in a crowded downtown

We designed a concept for a PAV named Pendul’Air. The idea of this sub-project was to design and size a full-scape PAV and to build a low-scale model of it. The full-scale prototype would be 4.2m high by 4.4m large with a central section of 1.2m. It is a VTOL platform. With current technology, we can expect a electric flight time of about 20min. With a computed total weight of about 340kg, it should transport 1 passenger at 100kph in an autonomous way.


  • Max Planck Institute for Biological Cybernetics (project leader)
  • ETH Zürich
  • Karlsruhe Institute of Technology
  • University of Liverpool
  • DLR Braunschweig
  • EPFL CVLab


Motility and Societal Transformations

V. Kaufmann 

Mobility / Society ; Zürich: Lars Müller Publishers, 2023-11.

Photocatalyzed [2σ + 2σ] and [2σ + 2π] Cycloadditions for the Synthesis of Bicyclo[3.1.1]heptanes and 5- or 6-Membered Carbocycles

T. V. T. Nguyen; A. Bossonnet; M. D. Wodrich; J. Waser 

Journal of the American Chemical Society. 2023. Vol. 145, num. 46, p. 25411-25421. DOI : 10.1021/jacs.3c09789.

A Topological Data Analysis of Navigation Paths within Digital Libraries

B. Kaabachi; S. Dumas Primbault 

2023-11-23. Computational Humanities Research 2023, Paris, France, December 6-8, 2023. p. 111-134.

Sustaining Knowledge and Governing its Infrastructure in the Digital Age: An Integrated View

P. Mounier; S. Dumas Primbault 


The Societal and Scientific Importance of Inclusivity, Diversity, and Equity in Machine Learning for Chemistry

D. Probst 

CHIMIA. 2023. Vol. 77, num. 1/2, p. 56. DOI : 10.2533/chimia.2023.56.

Parameter-Free Molecular Classification and Regression with Gzip

J. Weinreich; D. Probst 


Alchemical analysis of FDA approved drugs

M. Orsi; D. Probst; P. Schwaller; J-L. Reymond 

Digital Discovery. 2023. Vol. 2, num. 5, p. 1289-1296. DOI : 10.1039/D3DD00039G.

Molecular set representation learning

M. Boulougouri; P. Vandergheynst; D. Probst 


An explainability framework for deep learning on chemical reactions exemplified by enzyme-catalysed reaction classification

D. Probst 

Journal of Cheminformatics. 2023. Vol. 15, num. 113. DOI : 10.1186/s13321-023-00784-y.

Modelling mode dependent lane discipline in hybrid traffic

G. Anagnostopoulos; N. Geroliminis 

2023-07-26. The Traffic Flow Theory and Characteristics Committee Summer Meeting (TFTC-2023), Amsterdam, Netherlands, July 26-28 2023.