SMART mobility via prediction, optimization and personalization

In this chapter, we present a methodological approach for Smart Mobility that integrates three key features: prediction, optimization, and personalization. They are integrated in such a way that when a travel menu is offered, predicted conditions are considered in the attributes of alternatives and optimized system-level policies are maintained....

Learning-Based Multi-UAV Flocking Control With Limited Visual Field and Instinctive Repulsion

This article explores deep reinforcement learning (DRL) for the flocking control of unmanned aerial vehicle (UAV) swarms. The flocking control policy is trained using a centralized-learning-decentralized-execution (CTDE) paradigm, where a centralized critic network augmented with additional information about the entire UAV swarm is utilized...