Malintha Fernando

Malintha Fernando, Ransalu Senanayake, Heeyoul Choi et al.

Autonomous mobility is emerging as a new disruptive mode of urban transportation for moving cargo and passengers. However, designing scalable autonomous fleet coordination schemes to accommodate fast-growing mobility systems is challenging primarily due to the increasing heterogeneity of the fleets, time-varying demand patterns, service area expansions, and communication limitations. We introduce the concept of partially observable advanced air mobility games to coordinate a fleet of aerial vehicles by accounting for the heterogeneity of the interacting agents and the self-interested nature inherent to commercial mobility fleets. To model the complex interactions among the agents and the observation uncertainty in the mobility networks, we propose a novel heterogeneous graph attention encoder-decoder (HetGAT Enc-Dec) neural network-based stochastic policy. We train the policy by leveraging deep multi-agent reinforcement learning, allowing decentralized decision-making for the agents using their local observations. Through extensive experimentation, we show that the learned policy generalizes to various fleet compositions, demand patterns, and observation topologies. Further, fleets operating under the HetGAT Enc-Dec policy outperform other state-of-the-art graph neural network policies by achieving the highest fleet reward and fulfillment ratios in on-demand mobility networks.

Malintha Fernando

This work presents a novel, inference-based approach to the distributed and cooperative flocking control of aerial robot swarms. The proposed method stems from the Unmanned Aerial Vehicle (UAV) dynamics by limiting the latent set to the robots' feasible action space, thus preventing any unattainable control inputs from being produced and leading to smooth flocking behavior. By modeling the inter-agent relationships using a pairwise energy function, we show that interacting robot swarms constitute a Markov Random Field. Our algorithm builds on the Mean-Field Approximation and incorporates the collective behavioral rules: cohesion, separation, and velocity alignment. We follow a distributed control scheme and show that our method can control a swarm of UAVs to a formation and velocity consensus with real-time collision avoidance. We validate the proposed method with physical UAVs and high-fidelity simulation experiments.

Malintha Fernando, Lantao Liu

Swarms are highly robust systems that offer unique benefits compared to their alternatives. In this work, we propose a bio-inspired and artificial potential field-driven robot swarm control method, where the swarm formation dynamics are modeled on the basis of Markov Random Field (MRF) optimization. We integrate the internal agent-wise local interactions and external environmental influences into the MRF. The optimized formation configurations at different stages of the trajectory can be viewed as formation "shapes" which further allows us to integrate dynamics-constrained motion control of the robots. We show that this approach can be used to generate dynamically feasible trajectories to navigate teams of aerial robots in complex environments.