TAS for Cats: An Artist-led Exploration of Trustworthy Autonomous Systems for Companion Animals (2023)
Conference Proceeding

Cat Royale is an artist-led exploration of trustworthy autonomous systems (TAS) created by the TAS Hub's creative ambassadors Blast Theory. A small community of cats inhabits a purpose built 'cat utopia' at the centre of which a robot arm tries to en... Read More about TAS for Cats: An Artist-led Exploration of Trustworthy Autonomous Systems for Companion Animals.

Somabotics Toolkit for Rapid Prototyping Human-Robot Interaction Experiences using Wearable Haptics (2023)
Presentation / Conference

This work-in-progress paper presents a prototyping toolkit developed to design haptic interaction experiences. With developments in wearable and sensor technologies, new opportunities arise everyday to create rich haptic interaction experiences actin... Read More about Somabotics Toolkit for Rapid Prototyping Human-Robot Interaction Experiences using Wearable Haptics.

Resolving conflicts during human-robot co-manipulation (2023)
Conference Proceeding

This paper proposes a machine learning (ML) approach to detect and resolve motion conflicts that occur between a human and a proactive robot during the execution of a physically collaborative task. We train a random forest classifier to distinguish b... Read More about Resolving conflicts during human-robot co-manipulation.

ScoutWav: Two-Step Fine-Tuning on Self-Supervised Automatic Speech Recognition for Low-Resource Environments (2022)
Conference Proceeding

Recent improvements in Automatic Speech Recognition (ASR) systems obtain extraordinary results. However, there are specific domains where training data can be either limited or not representative enough, which are known as Low-Resource Environments (... Read More about ScoutWav: Two-Step Fine-Tuning on Self-Supervised Automatic Speech Recognition for Low-Resource Environments.

Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learning (2022)
Conference Proceeding

Efficient robotic manipulation of objects for sorting and searching often rely upon how well the objects are perceived and the available grasp poses. The challenge arises when the objects are irregular, have similar visual features (e.g., textureless... Read More about Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learning.

Patient, carer, and staff perceptions of robotics in motor rehabilitation: a systematic review and qualitative meta-synthesis (2021)
Journal Article

Background: In recent years, robotic rehabilitation devices have often been used for motor training. However, to date, no systematic reviews of qualitative studies exploring the end-user experiences of robotic devices in motor rehabilitation have bee... Read More about Patient, carer, and staff perceptions of robotics in motor rehabilitation: a systematic review and qualitative meta-synthesis.

Intelligent control of exoskeletons through a novel learning-from-demonstration method (2020)
Presentation / Conference

We present a novel concept that enables the intelligent and adaptive control of exoskeletons through exploiting our state-of-the-art learning from demonstration (LfD) method, namely Conditional Neural Movement Primitives (CNMPs) [1], on our integrate... Read More about Intelligent control of exoskeletons through a novel learning-from-demonstration method.