Jingqiang Wang
Papers
3
Total Citations
49
H-Index
3
About
Jingqiang Wang is a robotics researcher specializing in imitation learning, fine manipulation, and human-robot interaction, with a particular focus on the innovative use of chopsticks as a platform for studying complex dexterous manipulation challenges. Wang's most notable contribution, "Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation" (2021), has garnered 34 citations and addresses one of the core challenges in learning from demonstration — covariate shift — by leveraging human demonstrations to train robotic systems capable of handling small, slippery, and irregularly shaped objects. This work positions chopstick manipulation as a richly complex and ecologically valid testbed for advancing robotic dexterity. Complementing this, Wang's 2020 study on telemanipulation with chopsticks (11 citations) investigates human factors in user demonstrations, providing critical insights into how human adaptability can inform robotic system design. Together, these works reflect Wang's broader mission to bridge human skill and machine learning, drawing on culturally rich, real-world tools to push the boundaries of model-free imitation learning and fine manipulation robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3