A5041721293- Social Robot Interaction and HRI
- Human-Automation Interaction and Safety
- Magnetic Bearings and Levitation Dynamics
- Speech and dialogue systems
- Design Education and Practice
- AI in Service Interactions
- Structural Health Monitoring Techniques
- Data Visualization and Analytics
- Aesthetic Perception and Analysis
- Topic Modeling
- Ethics and Social Impacts of AI
- Explainable Artificial Intelligence (XAI)
- Vibration Control and Rheological Fluids
- Robotics and Automated Systems
- Advanced Text Analysis Techniques
- Machine Fault Diagnosis Techniques
- Robotic Mechanisms and Dynamics
- Video Analysis and Summarization
- Underwater Vehicles and Communication Systems
- Tribology and Lubrication Engineering
- Hydraulic and Pneumatic Systems
- Maritime Navigation and Safety
- Manufacturing Process and Optimization
- Color perception and design
- Multi-Agent Systems and Negotiation
Heriot-Watt University
2015-2024
Imperial College London
1994-2003
Imperial Valley College
1995
Iowa State University
1971
Robots are rapidly gaining acceptance in recent times, where the general public, industry and researchers starting to understand utility of robots, for example delivery homes or hospitals. However, it is key how instil appropriate amount trust user. One aspect a trustworthy system its ability explain actions be transparent, especially face potentially serious errors. Here, we study various aspects transparency interaction effect scenario robot performing triage when suspected Covid-19...
Stopword removal is a critical stage in many Machine Learning methods but often receives little consideration, it interferes with the model visualizations and disrupts user confidence. Inappropriately chosen or hastily omitted stopwords not only lead to suboptimal performance also significantly affect quality of models, thus reducing willingness practitioners stakeholders rely on output visualizations. This paper proposes novel extraction method that provides corpus-specific probabilistic...
As unmanned vehicles become more autonomous, it is important to maintain a high level of transparency regarding their behaviour and how they operate. This particularly in remote locations where cannot be directly observed. Here, we describe method for generating explanations natural language autonomous system reasoning. Our involves deriving an interpretable model autonomy through having expert ‘speak aloud’ providing various levels detail based on this model. Through online evaluation study...
Abstract Cognitive load has been widely studied to help understand human performance. It is desirable monitor user cognitive in applications such as automation, robotics, and aerospace achieve operational safety improve experience. This can allow efficient workload management avoid or reduce error. However, tracking real time with high accuracy remains a challenge. Hence, we propose framework detect by non-intrusively measuring physiological data from the eyes heart. We exemplify evaluate...
We present the UK Robotics and Artificial Intelligence Hub for Offshore Certification of Assets (ORCA Hub), a 3.5 year EPSRC funded, multi-site project. The ORCA vision is to use teams robots autonomous intelligent systems (AIS) work on offshore energy platforms enable cheaper, safer more efficient working practices. will research, integrate, validate deploy remote AIS solutions that can operate with existing future assets sensors, interacting safely in or semi-autonomous modes complex...
The world has seen in 2020 an unprecedented global outbreak of SARS-CoV-2, a new strain coronavirus, causing the COVID-19 pandemic, and radically changing our lives work conditions. Many scientists are working tirelessly to find treatment possible vaccine. Furthermore, governments, scientific institutions companies acting quickly make resources available, including funds opening large-volume data repositories, accelerate innovation discovery aimed at solving this pandemic. In paper, we...
Automated tools are increasingly being used to generate highly engaging concept maps as an aid strategic planning and other decision-making tasks. Unless stakeholders can understand the principles of underlying layout process, however, we have found that they lack confidence therefore reluctant use these maps. In this paper, present a qualitative study exploring effect on users' using data-driven explanation mechanisms, by conducting in-depth scenario-based interviews with ten participants....
Cognitive styles theories suggest that we divide into visual and verbal thinkers. In this paper describe a method designed to encourage communication between designers their audiences. This new feedback is based on enabling fast intuitive selections by the crowd from image banks when responding an idea. Visual summarization reduces massed choices small number of representative images. These summaries are then consumed at glance receiving leading thoughtful reflection designs. We report...
As robots take on roles in our society, it is important that their appearance, behaviour and personality are appropriate for the job they given perceived favourably by people with whom interact. Here, we provide an extensive quantitative qualitative study exploring robot but, importantly, respect to individual human traits. Firstly, show can accurately portray a social robot, terms of extroversion-introversion using vocal cues linguistic features. Secondly, through garnering preferences...
Autonomous systems are designed to carry out activities in remote, hazardous environments without the need for operators micro-manage them. It is, however, essential that maintain situation awareness order monitor vehicle status and handle unforeseen circumstances may affect their intended behaviour, such as a change environment. We present MIRIAM, multimodal interface combines visual indicators of with conversational agent component. This offers fluid natural way gain information on faults,...
This paper describes a laser-based system for measuring vibration on rotating discs. The setup allows the user to track an arbitrary periodic path at any multiple of disc's rotational speed. In particular, laser can be rotationally-locked disc and thus circle in space allowing continuous measurement response defined point both constant varying rotation An electro-magnetic non-contacting shaker provides forcing excitation disc. Due rotation, spectrum becomes very complex. vibrates several...
Autonomous systems in remote locations have a high degree of autonomy and there is need to explain what they are doing why , order increase transparency maintain trust. This particularly important hazardous, high-risk scenarios. Here, we describe multimodal interface, MIRIAM, that enables vehicle behaviour be queried by the user, along with mission status. These explanations, as part help improve operator's mental model can can't do, assist operator training.
We present MIRIAM (Multimodal Intelligent inteRactIon for Autonomous systeMs), a multimodal interface to support situation awareness of autonomous vehicles through chat-based interaction. The user is able chat about the vehicle's plan, objectives, previous activities and mission progress. system mixed initiative in that it pro-actively sends messages key events, such as fault warnings. will demonstrate using SeeByte's SeeTrack command control Neptune autonomy simulator.
Public perceptions of Robotics and Artificial Intelligence (RAI) are important in the acceptance, uptake, government regulation research funding this technology. Recent has shown that public's understanding RAI can be negative or inaccurate. We believe effective public engagement help ensure opinion is better informed. In paper, we describe our first iteration a high throughput in-person activity. use light touch quiz-format survey instrument to integrate in-the-wild participation into...
Studying Human-Robot Interaction over time can provide insights into what really happens when a robot becomes part of people's everyday lives. "In the Wild" studies inform design social robots, such as for service industry, to enable them remain engaging and useful beyond novelty effect initial adoption. This paper presents an experiment where we explored evolution interaction between users Robo-Barista. We show that perceived trust prior attitudes are both important factors associated with...
There are many challenges when it comes to deploying robots remotely including lack of operator situation awareness and decreased trust. Here, we present a conversational agent embodied in Furhat robot that can help with the deployment such remote by facilitating teaming varying levels control.
Autonomous systems in remote locations have a high degree of autonomy and there is need to explain what they are doing why order increase transparency maintain trust. Here, we describe natural language chat interface that enables vehicle behaviour be queried by the user. We obtain an interpretable model through having expert 'speak out-loud' provide explanations during mission. This approach agnostic type as operator from same user-group, predict these will align well with operator's mental...
Research into creating visualisations that organise ideas concise concept maps often focuses on implicit mathematical and statistical theories which are built around algorithmic efficacy or visual complexity. Although there multiple techniques attempt to mathematically optimise this multi-dimensional problem, it is still unknown how create immediately understandable people. In paper, we present an in-depth qualitative study observing the behaviour discussing strategy used by non-expert...