Soft Robots and Interfaces

Point of contact: Wenjie (Jeff) Li

We combine theoretical, computational, and experimental methods to study the fundamental mechanics of soft materials and structures and translate these insights into functional robotic hardware and physical interfaces.

Physics-Grounded Dexterous Manipulation

Point of contact: Mingrui Yu

Our research seeks to enable robots to interact with the physical world with human-like dexterity, reliability, and generalizability. We believe this requires robot intelligence to be grounded in the physics of interaction. To this end, we combine modeling, control, optimization, and learning, with current efforts spanning contact-rich dexterous manipulation and scalable physics simulation and learning.

Haptic Displays

Point of contact: Boyuan Liang

Haptic displays deliver virtual sense of touch to human users. Our goal is to build a high-density wearable haptic display whose pixels can cover the whole hand, and the driver system is compact enough to be sealed in fabrics. Applications include robot teleoperation and virtual reality.

Robot Learning

Point of contact: Yixiao Wang

In robot learning research, our goal is to analyze and address critical challenges in developing generalist robot policies capable of diverse tasks across varied environments. Our current efforts focus on effective and scalable multimodal reasoning (vision, force, language) and policy representation learning, continual learning, and their generalizations.

Embodied AI and Loco-manipulation

Point of contact: Yuxin Chen

Our research in Embodied AI and Loco-manipulation pushes the boundaries of both high-level reasoning and low-level planning/control for robots with diverse physical embodiments operating in open-vocabulary, real-world environments. We focus on the full life cycle of embodied AI systems, from data collection to deployment.

Data-Centric Robot Learning

Point of Contact: Chensheng Peng and Ruihai Wu

Our research in Data-Centric Robot Learning investigates how diverse sources of experience—including real-world robot trajectories, large-scale simulation, and human video data—can be systematically collected, generated, aligned, and leveraged to build scalable and generalizable robotic intelligence. We study data representations, generation pipelines, and learning methods that bridge domain and embodiment gaps across humans, simulated agents, and physical robots.

To learn more about the research done at MSC in the past, you can download a research booklet here or check the “Previous Porjects” below.