Lecheng Wang
Papers
3
Total Citations
20
H-Index
2
About
Lecheng Wang is a researcher at the forefront of embodied AI and robot manipulation, with a primary focus on advancing multi-embodiment intelligence and human-robot interaction. His most impactful contribution is the development of **RoboMIND (Multi-embodiment Intelligence Normative Data for Robot Manipulation)**, a landmark dataset comprising 107,000 demonstration trajectories across 479 diverse tasks involving 96 object classes. This work, which has garnered 14 citations since its 2025 release, provides a critical benchmark for training and evaluating robot manipulation policies across different hardware platforms. Wang’s earlier research also explored creative human-robot interfaces, notably developing a story generation system for children’s robots that transforms simple quick-draw sketches into narrative stories using a Multitask Transformer Network, addressing the challenge of sparse, unlabelled input data. By bridging the gap between low-level robotic control and high-level cognitive tasks, Wang’s work is helping to define the standards for normative data in robot learning, making him a key contributor to the scalable, generalizable robot intelligence that will power the next generation of autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2From Quick-draw To Story: A Story Generation System for Kids’ Robot4 citations · 2019
- 3