Below are some representative publications in each research interest. Please visit Publications page for a full list.
Human-autonomy alignment
We develop certifiable, efficient, and empowering methods to enable robots to align their autonomy with human users through various natural interactions.
- Robot learning from general human interactions
- Planning and control for human-robot systems
Robust Reward Alignment via Hypothesis Space Batch Cutting
arXiv preprint, 2025
Paper
Code (coming soon)
Video (coming soon)
Contact-rich dexterous manipulation
We develop efficient physics-based representations/modeling, planning/control methods to enable robots to gain dexterity through frequently making or breaking contacts with objects
- Learning, planning, and control for contact-rich manipulation
- Computer vision and learnable geometry for dexterous manipulation
Adaptive Barrier Smoothing for First-Order Policy Gradient with Contact Dynamics
International Conference on Machine Learning (ICML), 2023
Fundamental methods in robotics
We develop fundamental algorithms for efficient, safe, and robust robot intelligence, by harnessing the complementary benefits of model-based and data-driven approaches.
- Optimal control, motion plannig, reinforcement learning
- Differentiable optimization, inverse optimization
- Hybrid system learning and control
Enforcing Hard Constraints with Soft Barriers: Safe-driven Reinforcement Learning in Unknown Stochastic Environments
International Conference on Machine Learning (ICML), 2023
A Differential Dynamic Programming Framework for Inverse Reinforcement Learning
Submitted to IEEE Transactions on Robotics (T-RO), 2024