Malintha Fernando

PhD Candidate | Robotics
Indiana University, Bloomington

malintha.jpg

Hello! - ආයුබෝවන්! - Āyubōvan!

I am a PhD student working in multi-robot systems. My research revolves around the question: How can we coordinate connected, heterogeneous robot fleets to achieve group objectives in a scalable and a cooperative manner? I work at the intersection of autonomous mobility, unmanned aerial vehicles, multi-agent systems, reinforcement learning, and probabilistic graphical models. The applications of my research include advanced air mobility, mobile wireless networks, robot formation control, etc.

News

Apr, 2023 My first-author paper “Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility” got accepted to “Robotics: Science and Systems” conference! Looking forward to attend my first in-person RSS in South Korea!
Apr, 2023 Successfully concluded my PhD proposal (green light meeting). Currently planning to defend my thesis sometime in August 🤞
Mar, 2023 I am serving as a reviewer of 4 papers for IEEE Robotics and Automation Letters (RA-L) journal and IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Feb, 2023 A new preprint is out. I discuss the coordination of an eVTOL fleet in an AAM environment through the lens of partially observable stochastic games (POSG). A novel heterogeneous graph attention encoder-decoder is proposed for solving the POSG with multi-agent reinforcement learning [Preprint]
Feb, 2023 I am serving as a reviewer for International Journal of Robust and Nonlinear Control.

Selected Research Projects


Graph Attention Aerial Fleet Coordination

Advanced air mobility (AAM) aims at moving cargo and passengers using autonomous eVTOLs. I propose a multi-agent AAM autonomy for decentralized coordination of fully-autonomous heterogeneous eVTOL fleet using a graph-attention reinforcement-learning. The two images corresponds to two different eVTOL fleets using a single policy operating under different conditions [Preprint].

Two eVTOL fleets of 6 (Left) and 10 (Right) vehicles. The environment on the right has more depots and client nodes.
Graphical Game-Theoretic Communication-Aware Coverage

Wireless communication plays a crucial role in distributed coordination control of robot swarms. In this work we propose a robust, real-time coverage control approach for UAV swarms to provide the wireless coverage for a ground robot team using a UAV team operating over large geographic region with the local communication. The two images show a static and mobile ground robot team, where the UAV fleet is changing their formation to maximize the coverage for the ground robots. The dynamic communication links among the UAVs are shown in grey.
Checkout the full demo on Youtube .

Two static (Left) and moving (Right) ground robot fleets.
Real-Time Distributed Flocking Control

Murmurations are one of the most beatiful natural phenomena in the world, and characterizes the perfect swarm . In this work I tried to recreate the flocking characteristics UAVs using a variational inference approach in a distributed manner. The drones only uses their local observations to infer the control actions from feasible set; which makes this approach unique compared to the literature which we can guarantee the covergence and the dynamical feasibility.
Checkout the full demo on Youtube .

Left:A real robot demonstration using Crazyflie nano-drone team. Right: Two Carzyflie teams merging in simulation.
Multi-UAV Formation Control

Drone formation control has been gaining a lot of attention lately with applications ranging from entertainment to and defense industries. In this work I propose a rigid-body-based formation controlling approach with drone aggressive trajectory generation. The drones showed the ability to move at 2.5ms-1 (over 10 body-lengths a second) in a user defined formation with real-time receding horizon trajectory planning.
Checkout the formation control demo on Youtube .
Checkout the minimum-jerk trajectory generation demo on Youtube .

Left: Drone team of 5 moving in pentagon formation in a small indoor environment. Right: A SloMO of a Single UAV moving with precise aggressive motion through traffic cones in a minimum-jerk trajectory.

Selected Publications

  1. aam.webp
    Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility
    Malintha Fernando, Ransalu Senanayake, Heeyoul Choi, and 1 more author
    2023
  2. flocking.webp
    Online flocking control of UAVs with mean-field approximation
    Malintha Fernando
    In 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021

Cover image story: A Starling murmuration over a lake, which incidently looked liked a giant bird. Starlings (among many other animals) can coordinate their movements in thousands strong swarms in harmoneous, cohesive motions to evade predators; possibly characterizing the ideal swarm. More about the cover image.