Papers
7
Total Citations
458
H-Index
5
About
Liming Chen is a leading researcher in robotic manipulation and machine learning, with a primary focus on advancing robotic grasping and reinforcement learning. His most impactful contribution is the creation of the **Jacquard dataset** (2018), a large-scale, labeled dataset for robotic grasp detection that has garnered over **360 citations**. This dataset has become a cornerstone for training deep neural networks in grasp prediction, enabling robots to perform complex manipulation tasks in real-world applications. Chen also developed **panda-gym** (2021), a set of open-source, goal-conditioned reinforcement learning environments for the Franka Emika Panda robot, which has been widely adopted for multi-goal RL research. His work on **Scoring Graspability based on Grasp Regression** (2021), presented at the prestigious IEEE International Conference on Robotics and Automation (ICRA), further refines grasp prediction by integrating regression techniques. Beyond robotics, Chen has explored face age classification using deep hybrid models and developmental Bayesian optimization with visual similarity-based transfer learning. His research consistently bridges the gap between theoretical machine learning and practical robotic systems, making him a pivotal figure in the field of autonomous manipulation and intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1Jacquard: A Large Scale Dataset for Robotic Grasp Detection360 citations · 2018
- 2panda-gym: Open-source goal-conditioned environments for robotic learning37 citations · 2021
- 3Scoring Graspability based on Grasp Regression for Better Grasp Prediction20 citations · 2021
- 4Jacquard: A Large Scale Dataset for Robotic Grasp Detection18 citations · 2018
- 5Face age classification based on a deep hybrid model14 citations · 2018
- 6
- 7