Colin Rennie
Papers
4
Total Citations
199
H-Index
3
About
Colin Rennie is a robotics researcher whose work spans two compelling frontiers: robot perception for industrial automation and locomotion control for novel robotic systems. He is perhaps best known for his foundational contributions to RGBD-based object detection and pose estimation in warehouse environments, where his 2016 dataset paper has garnered an impressive 184 citations, establishing it as a key resource for researchers tackling the challenging problem of robotic pick-and-place operations. By providing structured visual data for detecting object poses on warehouse shelves, Rennie's work has meaningfully advanced the practical deployment of robotic manipulators in real-world logistics settings. Beyond industrial robotics, Rennie has also explored the cutting edge of soft and tensegrity robotics, investigating how rhythmic gait libraries and Bayesian optimization can be leveraged to control the notoriously complex, high-dimensional motion of spherical tensegrity robots. These contributions reflect a researcher comfortable bridging the gap between machine learning, control theory, and physical robot systems. Together, his body of work demonstrates a consistent drive to solve difficult, real-world robotics challenges — from warehouse floors to entirely new classes of compliant, adaptable machines — making him a valuable contributor to the broader robotics research community.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4