Augusto Loureiro da Costa

About

Augusto Loureiro da Costa is a leading researcher in cognitive robotics and multi-agent systems, with a focus on bridging the gap between reactive control and high-level symbolic reasoning. His most influential work, "From Reactive to Cognitive Agents" (2013, 7 citations), introduces a novel methodology that integrates Reinforcement Learning with Knowledge-Based Systems, enabling agents to autonomously generate symbolic knowledge bases from environmental interactions. This foundational contribution has shaped how autonomous systems learn and reason. Costa has also made significant strides in formation control, sensor fusion, and real-time embedded systems for mobile robotics, including a low-cost microprocessed controller for omnidirectional robots (2011, 3 citations). His work on cooperative multi-agent systems and cognitive architectures, such as the Concurrent Autonomous Agent deployed on a NAO humanoid robot (2015, 2 citations), demonstrates his commitment to advancing intelligent, collaborative robots. Additionally, his MecaTeam framework (2008, 2 citations) streamlined the development of simulated soccer agents for RoboCup, reflecting his impact on both theoretical and applied robotics. With a career spanning from dynamic social knowledge (2002) to distributed NMPC (2015), Costa’s research continues to influence the design of adaptive, knowledge-driven autonomous systems.

Research Focus

Key Achievements

Top Papers

1. 1
   From Reactive to Cognitive Agents: Extending Reinforcement Learning to Generate Symbolic Knowledge Bases

   7 citations · 2013
2. 2
   Distributed Constrained NMPC with Infeasibility Handling Applied to Formation Control of Nonholonomic Vehicles

   4 citations · 2015
3. 3
   An Architecture of Sensor Fusion for Spatial Location of Objects in Mobile Robotics

   4 citations · 2005
4. 4
   Real-time microprocessed system applied to mobile robots control

   3 citations · 2011
5. 5
   COOPERATIVE MOBILE ROBOTS: A COGNITIVE MULTI-AGENT APPROACH

   3 citations · 2006
6. 6
   Dynamic Social Knowledge: The Timing Evidence

   2 citations · 2002
7. 7
   Omnidirectional mobile robots navigation: A joint approach combining reinforcement learning and knowledge-based systems

   2 citations · 2013
8. 8
   MecaTeam Framework: An Infrastructure for the Development of Soccer Agents for Simulated Robots

   2 citations · 2008
9. 9
   Embedding the Concurrent Autonomous Agent into a Humanoid Robot**This work was supported by CAPES (Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, process number 9174-11-7), CNPq (Conselho Nacional de Desenvolvimento Científico e Tecnológico) and FAPESB (Fundação de Amparo à Pesquisa do Estado da Bahia).

   2 citations · 2015

Key Collaborators

Contact & Links