Sumários

Cancelada

13 maio 2026, 14:00 • Pedro Urbano Lima

devido a apresentação da CAOF-IA aos Presidentes de Departamento.

Multi-Robot Systems II

6 maio 2026, 14:00 • Pedro Urbano Lima

MRS: Cooperative Localization. Formation Control. Task Allocation, Cooperative Planning.

Partially Observable Markov Decision Processes (POMDP): algorithm derivation highlights. Reinforcement Learning. Model-free RL algorithms (Q-Learning, SARSA). Exploration vs Exploitation. Policy-Gradient methods. RL as Optimal Control.

Multi-Robot Systems I

29 abril 2026, 14:00 • Pedro Urbano Lima

MRS: Introduction. Cooperative Perception.

Physical AI

22 abril 2026, 14:00 • Pedro Urbano Lima

Digital2Physical Gap.

Learning from Demonstrations..

Foundation Models.

Reinforcement Learning

1 abril 2026, 14:00 • Pedro Urbano Lima

Value-gradient, Policy-gradient, Q-learning. SARSA. Deep RL