Carlos Soubervielle‐Montalvo
Papers
2
Total Citations
28
H-Index
2
About
Carlos Soubervielle‐Montalvo is a researcher at the forefront of intelligent robotics and embedded systems, whose work bridges the gap between autonomous navigation and real-time computer vision. His research primarily focuses on service robotics, path planning, and low-power embedded architectures for video tracking. In a foundational 2016 study (17 citations), Soubervielle‐Montalvo pioneered the use of reinforcement learning for navigation and path planning on a Roomba robot, equipping it with a topological map to autonomously traverse building floors—a critical first step toward practical service robots for homes and hospitals. More recently, his 2022 work (11 citations) introduced a novel low-power embedded system based on a SoC-FPGA, integrating the Honeybee Search Algorithm for real-time video tracking. This innovation addresses the persistent challenge of detecting objects of interest in dynamic environments, with applications spanning robotics, unmanned vehicles, and industrial automation. By combining bio-inspired optimization with hardware-software co-design, Soubervielle‐Montalvo has demonstrated how to achieve efficient, high-performance tracking on resource-constrained platforms. His contributions are shaping the next generation of autonomous systems that are both intelligent and energy-conscious.
Research Focus
Key Achievements
Top Papers
- 1Navigation and path planning using reinforcement learning for a Roomba robot17 citations · 2016
- 2