Biography:
Jaime Boal obtained the degrees of Industrial Engineer (major in Electronics), M.Sc. in Research in Engineering Systems Modeling, and PhD from Comillas Pontifical University in 2010, 2012, and 2014, respectively. After finishing his PhD, he joined the Electronics, Control and Communications Department, where he currently teaches courses on Electronic Systems and Autonomous Mobile Robots. Since June 2019 he is also the Coordinator of the M.Eng. in Intelligent Industry.
He combines his teaching duties with research projects at the Institute for Research in Technology (IIT), mainly on topics related to robotics, artificial intelligence applications, and energy efficiency. As a result of his work on energy efficiency at the IIT, in May 2018 he co-founded a spin-off called Stemy Energy, in which he served as CTO until June 2024.
Areas of interest:
Autonomous mobile robots · Computer vision · Reinforcement learning · Internet of Things (IoT) · Industry 4.0 · Energy efficiency and flexibility
Experience:
Throughout his career he has focused on the tight integration of hardware and software. He has designed and developed electronic control boards and real-time software for embedded systems, connected these devices to cloud servers using IoT protocols with end-to-end encryption and mutual authentication, and implemented applications capable of managing multiple concurrent connections with low latency. He has also worked on the design of platforms based on microservices interconnected through REST APIs.
Skills:
- Languages: Spanish (native), English (C2), French (B1)
- Programming languages: Python, C, C++, SQL, MATLAB, LaTeX
- Operating systems: Windows, macOS, Linux, FreeRTOS
- Cloud computing: Google Cloud
- Frameworks and libraries: TensorFlow, OpenCV, ROS, ORY
- DevOps tools: Git, Docker
- Software: CoppeliaSim, TIA Portal
- Hardware: Raspberry Pi, Google Coral, dsPIC, Arduino, Particle, ESP32, Intel RealSense cameras
Current research interests:
Computer vision and reinforcement learning applied to industrial manipulators and mobile robots, Graph neural networks (GNN) generation, Explainable artificial intelligence (XAI), IoT energy efficiency platforms
Güitta-López, L., Boal, J., López López, A.J., Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agent. Applied Intelligence. Vol. 53, nº. 12, pp. 14903 - 14917, June 2023. [Online: November 2022] 
JCR: 3,400 Q2 (2023); - SJR: 1,193 Q2 (2023);
JCR: 4,474 Q1 (2020); 4,400 Q1 (2023) - SJR: 0,798 Q1 (2020); 1,520 Q1 (2023)
JCR: 2,219 Q2 (2019); 3,500 Q1 (2023) - SJR: 0,609 Q1 (2019); 0,970 Q1 (2023)
JCR: 1,554 Q4 (2016); 1,900 Q3 (2023) - SJR: Q2 (2016); 0,579 Q2 (2023)
JCR: 0,824 Q4 (2015); 1,900 Q3 (2023) - SJR: 0,579 Q2 (2023)
JCR: 0,688 Q4 (2014); 1,900 Q3 (2023) - SJR: Q2 (2014); 0,579 Q2 (2023)
JCR: 4,159 Q1 (2013); 9,000 Q1 (2023) - SJR: Q1 (2013); 2,110 Q1 (2023) 
