Our Mission
Greetings! Our mission is advancing embodied decision-making systems by facilitating their reliability
and generalizability across diverse tasks and environments.
This requires seamless interaction between simulated environments, real-world deployment, and human feedback.
The following figures show our pipeline.
Specifically, our featured projects include:
- Generative Simulation for Robot Data Synthesization:
We develop a data engine that generates unlimited robot control data in simulated environments and
enables its generalization to real-world applications.
- Sim2Real Deployment:
We aim to address real-world problems, which means the skills and policies we develop
must be validated through realistic applications across multiple applications.
- Human Feedbacks:
To align robot behavior with human expectations, we incorporate human feedback into the decision-making process during robot control.
- Inverse Constrained Reinforcement Learning (ICRL):
Additionally, we have a series of works on ICRL, including those published at:
ICLR[23]
[25-1]
[25-2]
ICML[24-1],
[24-2]
- Reinforcement Learning from Human Feedback (RLHF):
