Linlan Liu

About

Linlan Liu is a leading researcher in robotic perception and computer vision, with a focus on semantic segmentation under data-scarce conditions. Their most impactful work addresses the critical challenge of enabling robots to recognize and manipulate objects in cluttered, real-world environments—particularly when training data is limited. Liu’s approach, which combines innovative segmentation techniques with robust handling of shiny, transparent, and unseen object categories, was instrumental in winning the prestigious Amazon Robotics Challenge (ARC) 2017. This achievement demonstrated the practical power of their methods in high-stakes industrial settings. Their 2018 paper on this topic has garnered 52 citations, reflecting its influence on subsequent research in robotic grasping and few-shot learning. By tackling the dual hurdles of limited training data and novel object categories, Liu has advanced the frontier of autonomous manipulation, making their work essential reading for students and researchers in robotics, computer vision, and AI-driven automation.

Research Focus

Key Achievements

Top Papers

1. 1
   Semantic Segmentation from Limited Training Data

   52 citations · 2018
2. 2
   Semantic Segmentation from Limited Training Data

   5 citations · 2017

Key Collaborators

Contact & Links