» I-X Research Presentations: Dandan Zhang

I-X Research Presentations: Dandan Zhang

Key Details:

Time: 15.30-16.30
Date: Thursday 19 September
Location: In Person | I-X Conference Room | Level 5
Translation and Innovation Hub (I-HUB)
Imperial White City Campus
84 Wood Lane
London W12 0BZ

15.30 - 16.30
19/09/2024

Speaker

Dr Dandan Zhang

Dr Dandan Zhang is a Lecturer (equivalent to an Assistant Professor in the U.S.) in Biomedical Robotics within the Department of Bioengineering at Imperial College London. She also serves as a Lecturer in Artificial Intelligence and Machine Learning as part of the I-X initiative. Dr. Zhang leads the Multi-Scale Embodied Intelligence Lab, where her research focuses on the intersection of robotics, biomedicine, and artificial intelligence. Her lab is committed to developing innovative multi-scale robotic systems with advanced dexterous manipulation capabilities and integrated multi-modality perception. By embedding physical and artificial intelligence into these systems, the lab seeks to create autonomous robots that adapt seamlessly across various scales and environments, driving significant advancements in biomedicine. A recent key focus of her research is micro-robotics, particularly in biomedical applications with the potential to revolutionize personalized healthcare through early diagnostics and interventions.

Talk Title

Dexterous Optical Micro-Robotic System for Biomedical Research

Talk Summary

This presentation will showcase recent advancements in micro-robotic systems, focusing on the innovative application of non-contact optical manipulation using Optical Tweezers (OT). OTs are highly effective for precisely handling microscale objects, which is crucial for various biomedical applications. However, this technology encounters challenges, such as accurately localizing transparent microrobots in three-dimensional space. Moreover, controlling their rotation motions in non-parallel directions to the optical plane is challenging. To address these issues, we introduce a novel OT-based micro-robotic platform that offers dexterous manipulation with six degrees of freedom (DoFs) and precise depth and pose estimation under an optical microscope. The presentation will also cover the design, modeling, and fabrication of uniquely shaped microrobots. Actuated by OTs, these microrobots are intended for the cooperative manipulation of biological objects. Additionally, the integration of shape memory alloy (SMA)-based actuators within the 3D-printed structure enhances manipulation capabilities by enabling controlled contraction-and-release movements. Machine learning-based approaches will be employed for precise tracking, depth and pose estimation, closed-loop control, navigation in complex biofluidic environments, and grasping delicate, deformable biological objects. This advanced optical micro-robotic system aims to improve cell manipulation, tissue engineering, and microsurgery by providing enhanced perception and dexterous manipulation.

More Events

Aug
12

I-X Seminar: Rough Analysis and Anomalous Streams with Professor Terry Lyons

Multi modal streams of information arise naturally in many engineering contexts. Rough path theory is an area of mathematics that fuses the control theory of Sussmann, Brockett and Fleiss with the analysis of Young to form a calculus that can efficiently describe the interaction and evolution of complex oscillatory systems.

Sep
24

I-X Breaking Topics in AI Conference

We are excited to invite you to the second edition of I-X Breaking Topics in AI conference sponsored by Schmidt Sciences. The conference will serve as a platform for sharing cutting-edge knowledge, discussing emerging trends, and fostering collaborative efforts to advance the field further. Our speakers will give overview talks outlining what they consider to be the exciting breakthroughs and future challenges in their area. The conference will also feature Flash Talks and Research Poster competitions.

Oct
01

AI: Cutting-Edge Overviews and Tutorial Series with Dr Nicolas Boullé

Operator Learning is an emerging field at the intersection of machine learning, physics and mathematics, that aims to discover properties of unknown physical systems from experimental data. Popular techniques exploit the approximation power of deep learning to learn solution operators, which map source terms to solutions of the underlying PDE.