Affordance Detection & Grasping

We have developed new methods for affordance detection & grasping. See our work in IROS16, IROS17, ICRA18, IROS20, IROS23, ICRA24, ICRA24. Our IIT-AFF and Grasp-Anything dataset are large-scale datasets for affordance detection and grasping.

Foundation & Generative Model

We have utilized foundation models for language-driven grasping (IROS23) and endovascular intervention. We have proposed techniques to combine LLM for generative tasks such as scene synthesis (NeurIPS23) and group dance (CVPR23, SIGGRAPH Asia23).

Efficient AI

Efficient models with real-time inference play an important role in robotics, medical, and manufacturing applications. We have developed lightweight models for autonomous driving (IROS20, IV22), medical imaging (TMI22), and federated learning (ICCV23).

Autonomous Catheterization

We have led research in developing world-first autonomous catheterization robot (ICRA20, ICRA20, TBME21, TBME22). We also developed CathSim, a realistic and high fidelity open-source simulator for endovascular intervention Arvix23 and the code.

Medical Imaging

We have proposed solutions to tackle challenging problems in medical imaging such as depth estimation (MICCAI21, MICCAI22), medical-VQA (MICCAI22), deformable registration (TMI22), and sensing area detection (MICCAI23).

Federated Learning

Collecting data to train big ML models violates the users’ privacy. We have proposed FL techniques to overcome this limitation. See our FL works for autonomous driving (IV22), non-IID data (ICRA24), topology design (ICCV23), and medical imaging (MICCAI23).