Papers
44
Total Citations
628
H-Index
16
About
Miguel Oliveira is a robotics and computer vision researcher whose work spans 3D object recognition, sensor calibration, and autonomous robot learning. His research has made significant contributions to the intersection of perception and manipulation in intelligent robotic systems, with a career trajectory that moves from locomotion control to sophisticated multi-sensor integration. Oliveira's early work explored bio-inspired locomotion, including head motion stabilization in quadruped robots and CPG-based gait optimization for bipeds. He later became known for developing GOOD, a global orthographic object descriptor for 3D recognition (58 citations), and for pioneering interactive, open-ended learning approaches that allow robots to recognize objects in unstructured environments. His 2018 paper on lifelong assistive robotics (56 citations) demonstrated how tightly coupling perception and manipulation enables robots to adapt over time in real-world settings. In recent years, Oliveira has focused on sensor calibration frameworks, producing widely adopted tools including ATOM (2022) and a ROS-based extrinsic calibration framework for intelligent vehicles, alongside a general hand–eye calibration approach (36 citations). Collectively, his publications have accumulated over 340 citations, reflecting sustained influence across academic and applied robotics communities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6The RACE Project25 citations · 2014
- 7ATOM: A general calibration framework for multi-modal, multi-sensor systems25 citations · 2022
- 8
- 9
- 10