Papers
14
Total Citations
831
H-Index
10
About
Trung Pham is a robotics researcher whose work sits at the intersection of semantic mapping, 3D scene understanding, and robotic manipulation. His research addresses one of the field's most fundamental challenges: enabling robots to perceive and interact with their environments in ways that are both geometrically precise and semantically meaningful. His highly cited paper "Meaningful Maps – Object-Oriented Semantic Mapping" (225 citations) exemplifies this vision, bridging the historically separate domains of geometric and semantic scene reconstruction. Pham has also made significant contributions to 6D object pose estimation, with his "Deep-6DPose" framework (129 citations) advancing RGB-based pose recovery for robotic applications. Perhaps most notably, Pham was a key contributor to the team behind Cartman, the low-cost Cartesian manipulator that claimed first place at the prestigious Amazon Robotics Challenge, a feat documented across multiple well-cited publications totaling over 170 citations. His related work on semantic segmentation from limited training data (52 citations) and reproducible robotic benchmarking (81 citations) further reflects a commitment to practical, real-world robotics research. With a body of work accumulating over 800 citations, Pham has established himself as an impactful voice in autonomous robotics and robot perception.
Research Focus
Key Achievements
Top Papers
- 1Meaningful maps – Object-oriented semantic mapping225 citations · 2017
- 2
- 3Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image129 citations · 2018
- 4
- 5
- 6Structure Aware SLAM Using Quadrics and Planes63 citations · 2019
- 7Semantic Segmentation from Limited Training Data52 citations · 2018
- 8Meaningful maps with object-oriented semantic mapping23 citations · 2017
- 9
- 10