A5039013002- Innovative Microfluidic and Catalytic Techniques Innovation
- Machine Learning in Materials Science
- Modular Robots and Swarm Intelligence
- Hand Gesture Recognition Systems
- Multimodal Machine Learning Applications
- Speech and dialogue systems
- Scientific Computing and Data Management
- Advanced Chemical Sensor Technologies
- Control Systems and Identification
- Gaussian Processes and Bayesian Inference
- Fault Detection and Control Systems
- Olfactory and Sensory Function Studies
- Hearing Impairment and Communication
- Industrial Vision Systems and Defect Detection
- Image and Object Detection Techniques
- IoT and Edge/Fog Computing
- Data Stream Mining Techniques
- Computational Drug Discovery Methods
- Mobile Crowdsensing and Crowdsourcing
- Soft Robotics and Applications
- Problem and Project Based Learning
- Action Observation and Synchronization
- Experimental Learning in Engineering
- Metabolomics and Mass Spectrometry Studies
- Nanomaterials and Printing Technologies
University of Liverpool
2022-2024
University of Edinburgh
2020
University of Manchester
2019-2020
This study presents a modular autonomous workflow for solid-state chemistry comprising three separate robots, allowing automated powder X-ray diffraction to underpin crystalline materials discovery.
Self-driving labs (SDLs) leverage combinations of artificial intelligence, automation, and advanced computing to accelerate scientific discovery.
An automated solid dispenser was developed using a dual-arm robot and fuzzy logic controller, mimicking the operations of human researchers.
Automated laboratory experiments have the potential to propel new discoveries, while increasing reproducibility and improving scientists' safety when handling dangerous materials. However, many automated workflows not fully leveraged remarkable advancements in robotics digital lab equipment. As a result, most robotic systems used labs are programmed specifically for single experiment, often relying on proprietary architectures or using unconventional hardware. In this work, we tackle problem...
Closed-loop experiments can accelerate material discovery by automating both experimental manipulations and decisions that have traditionally been made researchers. Fast non-invasive measurements are particularly attractive for closed-loop strategies. Viscosity is a physical property fluids important in many applications. It fundamental application areas such as coatings; also, even if viscosity not the key of interest, it impact our ability to do experimentation. For example, unexpected...
Abstract The extent to which languages share properties reflecting the non-linguistic constraints of speakers who speak them is key debate regarding relationship between language and cognition. A critical case spatial communication, where it has been argued that semantic universals should exist, if anywhere. Here, using an experimental paradigm able separate variation within a from languages, we tested use demonstratives—the most fundamental frequent terms across languages. In n = 874 29...
Automation can transform productivity in research activities that use liquid handling, such as organic synthesis, but it has made less impact materials laboratories, which require sample preparation steps and a range of solid-state characterization techniques. For example, powder X-ray diffraction (PXRD) is key method pharmaceutical chemistry, its end-to-end automation challenging because involves solid handling processing. Here we present fully autonomous workflow for PXRD experiments match...
Accelerating material discovery has tremendous societal and industrial impact, particularly for pharmaceuticals clean energy production. Many experimental instruments have some degree of automation, facilitating continuous running higher throughput. However, it is common that sample preparation still carried out manually. This can result in researchers spending a significant amount their time on repetitive tasks, which introduces errors prohibit production statistically relevant data....
The use of laboratory robotics for autonomous experiments offers an attractive route to alleviate scientists from tedious tasks while accelerating material discovery topical issues such as climate change and pharmaceuticals. While some experimental workflows can already benefit automation, sample preparation is still carried out manually due the high level motor function dexterity required when dealing with different tools, chemicals, glassware. A fundamental workflow in chemical fields...
With advances in the field of machine learning, service robots are envisioned to become more present. The COVID-19 pandemic has accelerated this need. One such example would be coffee shops, which have intrinsic our everyday lives. Yet, serving an excellent cup is not trivial as a blend typically comprises rich aromas, indulgent and unique flavours. Our work addresses by proposing computational model recommends optimal beans resulting from users' preferences. Given properties (objective...
In the early stages of infant development, gestures and speech are integrated during language acquisition. Such a natural combination is therefore desirable, yet challenging, goal for fluid human-robot interaction. To achieve this, we propose multimodal deep learning architecture, comprehension complementary gesture-word combinations, implemented on an iCub humanoid robot. This enables human-assisted learning, with interactions like pointing at cup labelling it vocal utterance. We evaluate...
With advances in the field of machine learning, precisely algorithms for recommendation systems, robot assistants are envisioned to become more present hospitality industry. Additionally, COVID-19 pandemic has also highlighted need have service robots our everyday lives, minimise risk human to-human transmission. One such example would be coffee shops, which intrinsic lives. However, serving an excellent cup is not a trivial feat as blend typically comprises rich aromas, indulgent and unique...
Modelling robot dynamics accurately is essential for control, motion optimisation and safe human-robot collaboration. Given the complexity of modern robotic systems, modelling remains non-trivial, mostly in presence compliant actuators, mechanical inaccuracies, friction sensor noise. Recent efforts have focused on utilising datadriven methods such as Gaussian processes neural networks to overcome these challenges, they are capable capturing without requiring extensive knowledge beforehand....
Performing a large volume of experiments in Chemistry labs creates repetitive actions costing researchers time, automating these routines is highly desirable. Previous robotic chemistry have performed high numbers autonomously, however, processes rely on automated machines all stages from solid or liquid addition to analysis the final product. In systems every transition between machine requires chemist pick and place glass vials, this currently using open loop methods which require...
Automated laboratory experiments have the potential to propel new discoveries, while increasing reproducibility and improving scientists' safety when handling dangerous materials. However, many automated workflows not fully leveraged remarkable advancements in robotics digital lab equipment. As a result, most robotic systems used labs are programmed specifically for single experiment, often relying on proprietary architectures or using unconventional hardware. In this work, we tackle problem...
Infants acquire language in distinct stages, starting from single gestures and words, through utilising gestures, they learn multi-word combinations. To achieve this development on artificial agents, we propose a multimodal computational model for to transition gesture-word Our approach relies advancements deep models feature extraction casting the supplementary word generation problem into matrix completion task. Experimental evaluation is carried out dataset recorded directly humanoid...
Self-driving labs (SDLs) leverage combinations of artificial intelligence, automation, and advanced computing to accelerate scientific discovery. The promise this field has given rise a rich community passionate scientists, engineers, social as evidenced by the development Acceleration Consortium recent Accelerate Conference. Despite its strengths, rapidly developing presents numerous opportunities for growth, challenges overcome, potential risks which remain aware. This perspective builds...
Performing a large volume of experiments in Chemistry labs creates repetitive actions costing researchers time, automating these routines is highly desirable. Previous robotic chemistry have performed high numbers autonomously, however, processes rely on automated machines all stages from solid or liquid addition to analysis the final product. In systems every transition between machine requires chemist pick and place glass vials, this currently using open loop methods which require...