Papers
4
Total Citations
133
H-Index
2
About
Jose Hoyos is a leading researcher in the field of robotics, with a focus on programming by demonstration and robotic assembly. His work centers on enabling robots to learn complex manipulation tasks from human demonstrations, significantly advancing the efficiency and autonomy of industrial automation. Hoyos’s most impactful contribution is his 2018 paper on "Trajectory generation for robotic assembly operations using learning by demonstration," which has garnered 105 citations, highlighting its influence on practical robotic applications. He has also pioneered the use of incremental learning in task-parameterized Gaussian mixture models (2015, 24 citations) to allow robots to adapt skills over time. In earlier work, Hoyos proposed the application of extreme learning machines for encoding trajectories in programming by demonstration (2013), offering advantages like rapid training and avoidance of local minima. Additionally, his research on screw and wrench orientation estimation using artificial vision on the NAO humanoid robot (2013) demonstrates his versatility in combining perception and control. Hoyos’s contributions are instrumental in making robotic assembly more flexible and intuitive, bridging the gap between human expertise and machine execution.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4