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 research involves the following aspects:
- Simulated environments:
We follow a generative simulation pipeline that enables the synthesis of infinite robot control data within simulated environments
and facilitates the scaling of this data to practical applications.
The detailed research topics includes:
- Sim2Real Data Engine: [In-Submission]
- Agentic Skill Discovery: [Work in Process]
- Real-world Deployment:
We aim to address real-world problems, which means the skills and policies we develop must be validated through realistic applications.
Ideally, these should be tested in real-world environments under everyday tasks to ensure their practicality and effectiveness.
In this context, working with hardware is crucial.
Our primary focus is on humanoid robots, specifically, dual-arm, legged robots equipped with dexterous hands.
The detailed research topics includes:
- Whole-body Locomotion: [In-Submission]
- Whole-body Manipulation: [Work in Process]
- Human Feedbacks:
We believe that one of the primary goals of embodied decision-making is to serve humans,
meaning that the decisions made by robots must align with human expectations.
To achieve this goal, we focus on incorporating human feedback into the decision-making process during robot control.
Such feedback signals mainly concern the safety and optimality (i.e., task completion) of the decisions.
The detailed research topics includes: