top of page

2023-2024 PhD Projects

You are welcome to apply for PhD in our lab!

01

Microrobots for Bottom-Up Tissue Engineering

Project Overview:

Tissue engineering offers innovative solutions for regenerating or replacing damaged tissues and organs. The traditional top-down approach often struggles to replicate the fine complexity and heterogeneity of native tissues. A bottom-up approach, using microrobots, could overcome these limitations, providing the precision and control required to assemble cellular constructs from the ground up. This PhD project will investigate and develop microrobots designed for bottom-up tissue engineering.

Project Objectives:

The primary objectives of this research project are:

Design and Development of Microrobots: Create microrobots capable of manipulating individual cells or small cellular clusters. These robots should exhibit biocompatibility, precise maneuverability, and capabilities to perform under biofabrication conditions.

Cell Assembly Techniques: Develop novel techniques and strategies for assembling cells into complex, multi-layered constructs using microrobots. This may involve arranging cells based on cell type, orientation, or spatial arrangement to mimic the native architecture of the target tissue.

Integration of Sensing Mechanisms: Incorporate sensing technologies into the microrobots, enabling them to respond to their microenvironment in real-time and adjust their actions accordingly during the assembly process.

Validation of Engineered Tissues: Test the functionality and viability of the engineered tissues in vitro and in vivo. This includes assessing cell survival, tissue integrity, and biological function, and comparing them to tissues engineered using traditional methods.

Expected Impact:

The successful completion of this project could revolutionize the field of tissue engineering, providing a novel approach for creating tissues that more accurately mimic their in vivo counterparts. This could significantly enhance the success rate of tissue-engineered implants and pave the way for the fabrication of more complex tissues or even whole organs.

This project offers an exciting opportunity for the PhD candidate to work at the cutting edge of tissue engineering and microrobotics, two rapidly advancing fields with the potential to significantly impact healthcare. The skills and knowledge acquired will be highly relevant for a variety of career paths, from academic research to biotechnology development.

02

Autonomous Micro/Nano-Robots for Targeted Treatment

Project Overview:

The advancement of autonomous micro/nano-robots offers the potential to transform targeted treatment strategies, especially in challenging fields like oncology, neurology, and cardiovascular diseases. These ultra-small robots can be navigated through the body to deliver drugs directly to disease sites, improving treatment efficacy while reducing systemic side effects. This PhD project aims to explore and develop autonomous micro/nano-robots that can perform targeted treatment in complex physiological environments.

Project Objectives:

The primary objectives of this research project are:

Design and Fabrication of Micro/Nano-Robots: Create biocompatible, maneuverable micro/nano-robots capable of carrying and releasing therapeutic payloads. The robots should have the ability to navigate through various body fluids and tissues to reach targeted sites.

Autonomous Navigation and Control: Develop advanced control algorithms for autonomous navigation and decision-making based on sensory feedback. This involves integrating machine learning and AI techniques with real-time data interpretation.

Therapeutic Payload Integration: Incorporate methods for loading therapeutic payloads onto the robots and controlled release mechanisms at the targeted site. This could involve chemotherapeutic agents for cancer, clot-dissolving drugs for thrombosis, or neuroprotective drugs for neurodegenerative diseases.

In Vitro and In Vivo Validation: Conduct rigorous testing of the micro/nano-robots in vitro (e.g., in cell cultures or organ-on-a-chip systems) and in vivo (e.g., in animal models) to evaluate their navigation capabilities, safety, and therapeutic efficacy.

Expected Impact:

The successful completion of this project has the potential to revolutionize targeted treatment strategies. By allowing for precise, localized delivery of therapies, autonomous micro/nano-robots can significantly increase treatment efficacy and reduce adverse side effects, leading to improved patient outcomes.

This PhD project offers the candidate an exciting opportunity to work at the cutting edge of medical robotics, nanotechnology, and targeted therapy. The acquired knowledge and skills will be highly valuable for a variety of career paths in academic research, healthcare technology, and pharmaceuticals.

03

Machine Learning-Based Perception of Microscopic Images for Biomedical Applications

Project Overview:

Microscopic images are an invaluable tool in biomedical research and clinical diagnostics. However, the wealth of information that these images contain can be difficult to interpret due to factors such as high-dimensionality, noise, and variability. This PhD project aims to harness the power of machine learning to enhance the perception and interpretation of microscopic images in biomedical applications, driving forward our capabilities in disease diagnosis, drug development, and understanding of biological processes.

Project Objectives:

The primary objectives of this research project are:

Challenges in Biomedical Microscopy: Investigate the unique challenges in interpreting microscopic images in the biomedical context, including issues related to biological variability, sample preparation artefacts, noise, and the need for precise and reliable quantification.

Develop Machine Learning Models: Design and implement machine learning algorithms tailored for the challenges and needs of microscopic image analysis in biomedicine. This could involve supervised learning for diagnostic tasks, unsupervised learning for discovery of unknown patterns, and reinforcement learning for sequential decision-making in image analysis.

Enhance Perception of Biomedical Microscopic Images: Apply the developed machine learning models to enhance the interpretation of biomedical microscopic images. This could involve tasks such as cell identification and classification, disease marker recognition, or morphological analysis.

Validation and Evaluation: Validate and test the developed algorithms using real-world biomedical microscopic data sets. This should include quantitative measures of performance and comparison with traditional image analysis methods.

Expected Impact:

The successful completion of this project could significantly advance the field of biomedical microscopy. Machine learning algorithms tailored to microscopic image analysis could provide more accurate and efficient analysis, accelerating biomedical research and improving clinical diagnostics.

This PhD project provides an exciting opportunity for the candidate to work at the intersection of machine learning, microscopy, and biomedicine. The skills and knowledge gained will be highly relevant for a range of career paths in academia, healthcare technology, biomedical research, and data science.

04

Modelling, Control, and Simulation of Microrobots in Complex Media

Project Overview:

Microrobots hold great promise in areas like healthcare, environmental monitoring, and materials engineering. Nonetheless, their operation in complex media introduces numerous challenges related to the microscale physical phenomena. This project aims to integrate the laws of physics into machine learning models to enhance the modelling, control, and simulation of microrobots navigating complex media.

 

Project Objectives:

The primary objectives of this research are:

Understanding Microscale Dynamics: Examine the unique challenges and dynamics involved in controlling microrobots in complex media, taking into account factors like microscale fluid dynamics, interaction forces, and non-linear behaviors.

Physics-Informed Machine Learning Models: Develop machine learning models informed by physical laws for improved prediction of microrobot dynamics in complex environments. This could include hybrid models, incorporating physics-based equations with data-driven machine learning methods.

Control and Simulation Algorithm Development: Implement these physics-informed machine learning models within advanced control algorithms and simulation tools tailored for microrobotic systems. This might involve various machine learning approaches such as reinforcement learning or other suitable algorithms for efficient control.

Experimental Validation: Test and validate the developed models and control algorithms using actual microrobotic systems in lab conditions that emulate complex media. Assess the robustness, performance, and adaptability of the models and control methods.

Expected Impact:

Successful execution of this project can result in significant advancements in the microrobotics field. Physics-informed machine learning has the potential to substantially improve control over microrobots in complex environments, potentially revolutionizing sectors such as healthcare, environmental monitoring, and materials engineering.

This project offers an exciting opportunity for the candidate to work at the intersection of robotics, machine learning, and physics, providing skills and knowledge beneficial to a broad range of career paths in academia, advanced manufacturing, biomedical engineering, and beyond.

05

Brain-Computer Interface for Assisted Robotics

Project Overview:

The fusion of Brain-Computer Interfaces (BCIs) and robotics holds transformative potential, particularly for assistive technologies aimed at improving the lives of individuals with mobility impairments. This PhD project aims to advance the development and application of BCIs in assistive robotics, enabling individuals to control robotic systems using their thoughts.

Project Objectives:

The primary objectives of this research project are:

Investigate BCI Techniques: Study existing BCI methods, with a focus on non-invasive techniques such as Electroencephalography (EEG) and functional Near-Infrared Spectroscopy (fNIRS). Understand their strengths, limitations, and suitability for integration with assistive robotics.

Develop BCI-Assisted Robotic Systems: Design and implement robotic systems that can be controlled through a BCI. This may involve prosthetic limbs, exoskeletons, or other assistive devices that can aid individuals with mobility impairments.

Refine Control Algorithms: Develop and optimize algorithms that translate brain signals into specific commands for the robotic system. This involves machine learning and signal processing techniques to interpret and classify brain signals.

System Evaluation and Optimization: Test the BCI-assisted robotic systems in real-world conditions with the intended users. Evaluate the system's performance, usability, and adaptability, and use this feedback for iterative improvements and optimization.

Expected Impact:

The successful completion of this project is expected to substantially impact the fields of neuroengineering, assistive technology, and robotics. By developing robust and user-friendly BCI-controlled robotic systems, this project could significantly enhance the independence and quality of life of individuals with mobility impairments.

Moreover, this project has the potential to advance our understanding of brain function, particularly in the context of human-machine interfaces, and to set new standards in the field of assistive robotics.

The PhD project offers an exciting opportunity for the candidate to work at the cutting edge of neuroscience, AI, and robotics. The knowledge and skills acquired will be highly relevant for a wide range of career paths in academia, healthcare technology, and neurorehabilitation.

06

Large Multimodal Models Based Robot Learning for Intelligent Medical Robotics

Project Overview:

The role of medical robotics in modern healthcare has expanded significantly over the last few years, paving the way for more sophisticated and precise interventions. However, the complex nature of medical environments and diverse types of data involved demand robust and versatile control systems. This PhD project aims to explore and develop large multimodal models for medical robotics, combining various data types like visual, auditory, sensor-based, and textual information to improve robotic capabilities and performance in medical settings.

Project Objectives:

The primary objectives of this project are:

Development of Large Multimodal Models for Healthcare: Create or fine-tune large-scale multimodal AI models capable of processing and integrating multiple types of data, such as images, sounds, tactile data, and texts. The models should efficiently manage and interpret this data to make informed decisions.

Integration with Medical Robotics: Incorporate these multimodal AI models into existing medical robotic systems. The goal is to enhance robotic capabilities, allowing them to perform tasks more autonomously and adaptively in various medical scenarios.

Performance Evaluation and Model Optimization: Conduct rigorous testing and evaluation of the integrated multimodal AI-robotic systems in both simulated and real-world medical environments. Use collected performance data to optimize the AI models and refine system integration for improved functionality.

Exploration of Potential Applications: Investigate the potential applications of these enhanced medical robotic systems in various aspects of healthcare, such as minimally invasive surgery, rehabilitation, diagnostics, and patient care.

 

Expected Impact:

The successful completion of this project is expected to contribute significantly to the field of medical robotics. The use of large multimodal models can transform the capabilities of medical robots, allowing them to respond adaptively to complex, multi-faceted medical scenarios.

Moreover, the enhanced ability of these robots to understand and navigate medical environments could potentially lead to improved surgical outcomes, more efficient diagnostic processes, and more effective patient care.

This PhD project provides an exceptional opportunity for the candidate to work on cutting-edge technologies in AI and medical robotics. The skills and knowledge acquired will be highly relevant for a variety of future career paths, from academic research to healthcare technology development.

07

Explainable Artificial Intelligence (XAI) for Trustworthy Intelligent Medical Robotics

Project Overview:

As the application of AI in medical robotics expands, ensuring transparency and trust in these systems becomes crucial. This project aims to delve into the intersection of Explainable Artificial Intelligence (XAI) and medical robotics to develop trustworthy intelligent systems that can provide understandable explanations for their decisions and actions.

 

Project Objectives:

The primary objectives of this research project are:

Exploring XAI Techniques: Investigate various methods and techniques within the field of XAI, including but not limited to model-agnostic methods, interpretable models, and visual explanation tools.

Development of XAI-Enhanced Medical Robots: Design and implement intelligent medical robots integrated with XAI capabilities. These robots should be able to provide clear, understandable explanations for their actions and decisions in a format that medical professionals can understand and use.

System Validation and Evaluation: Test and validate the developed XAI-enhanced robotic systems in various medical scenarios, focusing on their performance, the quality of their explanations, and their acceptability among medical professionals.

Enhancement of Trust and Acceptance: Study the impact of the developed XAI mechanisms on the trust and acceptance of intelligent medical robots among medical practitioners and patients.

Expected Impact:

The successful completion of this project is expected to significantly contribute to the fields of medical robotics and AI. By developing medical robotic systems that are not only intelligent but also explainable, this project could improve trust in AI, leading to wider acceptance and more effective utilization of such systems in the healthcare sector.

Furthermore, this project can potentially set new standards for accountability and transparency in AI-assisted healthcare services, improving patient safety and care quality.

This project provides a unique opportunity for the candidate to work at the cutting edge of medical robotics and AI. The knowledge and skills acquired will be invaluable in a variety of career paths, including academia, healthcare technology, and AI ethics.

08

Tactile Robotic Telemedicine

Project Overview:

The integration of robotics and telemedicine has paved the way for innovative healthcare services, allowing medical practitioners to remotely deliver care to patients. This project aims to investigate and develop the concept of Tactile Robotic Telemedicine further. We aspire to design and implement robotic systems capable of delivering tactile feedback, providing healthcare professionals with a more immersive and interactive telemedicine experience.

Project Objectives:

The central objectives of this research project are:

Development of Tactile Robotic Systems: Design and develop robotic systems equipped with tactile sensors that can simulate the sense of touch. The systems should be able to mimic the movements and actions of a healthcare provider remotely, based on their inputs.

Telemedicine Integration: Integrate these tactile robotic systems with existing telemedicine infrastructure, ensuring seamless communication and operation between the healthcare provider and the robotic system.

Tactile Feedback Analysis: Develop algorithms to analyze the tactile feedback data obtained from the robotic systems. This includes implementing machine learning techniques to interpret and understand the nuances of tactile interactions.

System Validation: Conduct rigorous testing and validation of the developed systems and algorithms. This involves creating controlled scenarios to evaluate the performance, reliability, and safety of the tactile robotic telemedicine systems.

 

Expected Impact:

The successful implementation of this project is set to revolutionize the telemedicine landscape by introducing a new dimension of interactivity in remote healthcare delivery. It will facilitate more comprehensive medical examinations, potentially allowing for remote procedures that require tactile feedback, such as physical therapy or certain diagnostic procedures.

This project's success could also increase access to healthcare services, particularly for patients in remote or underserved areas, by allowing healthcare providers to deliver a broader range of services remotely.

This project offers a unique opportunity to work at the intersection of robotics, telemedicine, and machine learning. The candidate will acquire valuable skills in these rapidly evolving fields, placing them at the forefront of technological innovation in healthcare.

bottom of page