"Experts note that robots have explored the deepest ocean floor and the surface of Mars, yet still do not function well within our own homes. How can we address this gap to enhance independence and safety for human beings?" Ravi Vaidyanathan
UK DRI Group Leader
Senior Lecturer in Bio-Mechatronics at Imperial College London, Dr Ravi Vaidyanathan is an expert in the application of mechanical engineering to medicine and biological systems. Obtaining his PhD in biologically inspired systems in 2001 from Case Western Reserve University, USA, he went on to work in industry before joining the University of Southampton in 2006. Ravi has authored over 200 scientific papers and holds two patents for bio-mechanical inventions. He brings his expertise to the UK DRI Care Research & Technology Centre at Imperial to lead an intriguing research programme investigating ‘social robots’ for people with dementia.
1. At a glance
Can interactive ‘social’ robots help improve the lives of people with dementia?
Dr Ravi Vaidyanathan is aiming to seize the exciting potential of artificial intelligence (AI) to improve dementia care. He is leading a team who will develop a family of robotic devices that can engage people living with dementia, helping improve safety in the home and enhancing quality of life.
The team will initially focus on designing social robotic systems that can respond to safety alerts within the home, such as a cooker being left on – or to certain behaviours, such as agitation or injury. Once triggered, the robot will engage with the individual and act to reduce risks. This may involve directing them to address the hazard – or deploying automated tools that can do so instead. By engaging in conversation, it may be possible to identify the cause of their agitation – such as confusion in the dark, pain or dehydration – and help point the individual towards a simple solution.
The researchers plan to make extensions to existing commercial technologies – such as Amazon’s Alexa – but they will also develop bespoke devices. They will closely involve people with dementia, family and carers during the design process to define the characteristics of prototype devices and test these to ensure these robots are safe, accessible and enjoyable for people to engage with.
2. Scientific goals
Interactive ‘social’ robots have already been used to engage and stimulate people living with dementia. They can: (a) undertake diverse behaviours; (b) collect rich data; (c) change the environment and (d) respond appropriately in a flexible, task-dependent manner. They provide a way to continuously monitor the home and engage with people to support behaviour or to provide companionship. However, their clinical potential is largely untapped and development of robotics for dementia care is at an early stage.
This UK DRI programme, led by Dr Ravi Vaidyanathan, will develop an automated ‘family’ of robotic devices focusing on improving safety in the home and enhancing the quality of life for a person living with dementia. Where possible, the team will build on existing commercial technology. For example, they will extend devices such as Amazon’s Alexa to provide a conversational agent that can be used by the robotic devices. However, they will also develop bespoke robotic solutions.
The robotic devices will be designed to be safe, accessible and enjoyable to engage with. A design sprint will be used to define key features and functionality. The team will develop a small number of exemplars providing proof-of-principle. For example, they will develop robotic systems to respond to (a) environmental alerts produced by the Healthy Home (e.g. noting a kitchen spillage or cooker left on); and (b) alerts related to the person with dementia (e.g. responding to signs of agitation or injury). Following an alert, the robot device will engage with the individuals and, guided by information from the Healthy Home, will act to reduce risks. They envisage that the simplest solution may be to direct the owner, e.g. to clean up a spillage, but it may be possible to deploy automated tools to achieve similar ends. In the case of agitation, if a cause can be identified such as confusion in the dark, pain or dehydration, simple interventions may be effective and interactions through a conversational agent or social robot may be directly beneficial.
A related focus for the programme will be to develop effective methods of communication between people with dementia and robotic devices. The design process will evaluate the impact of variations in features such as configurable visual appearance, voice characteristics, movement, and tactile features that are optimal for the individuals involved, and the team will produce ‘lightweight’ prototypes for testing purposes.
Main objectives and research goals:
1. To produce robotic devices with elementary AI that are capable of interacting with people living with dementia.
2. To integrate robotic devices within the Healthy Home to monitor and manage the environment for improved safety and quality of life.
3. To harness user-centred design to define the characteristics of robotic devices suitable for these tasks
3. Team members
Dr Maitreyee Wairagkar (Research Associate in Affective Robotics)
Dr Samuel Wilson (Research Associate in Cybernetics)
Dr Weiguang Huo (Research Associate in Human Augmentation)
Maria Rosposo Di Lima (Research Associate in Robotic Engagement with Humans)
Nathan Steadman (Research Associate in Brain-Robot Interface)
The Biomechatronics Laboratory is working closely with a range of medical and commercial collaborators to translate our basic research in robotics and human-machine interface (HMI) to working devices for patient care. A few of our closest collaborators include:
- Schizophrenia Research Foundation India (SCARF): The Biomechatronics Laboratory is involved with the Schizophrenia Research Foundation India (SCARF) on the introduction of robotic devices to help dementia patients in low and middle income countries
- Medical Research Council Brain Network Dynamics Unit, University of Oxford: The Biomechatronics Laboratory is working with the Medical Research Council Brain Network Dynamics Unit at the University of Oxford to use robots to assess and treat neurological conditions such as Parkinson’s Disease as well as quantify the role of deep brain local field potentials (LFPs) in movement.
- Imperial College Chairing Cross NHS Trust: We are involved in a range of projects at the Imperial College Chairing Cross NHS Trust. Our research there involves brain-machine interfaces for neurological disorders as well as control of artificial (prosthetic) limbs).
- Ossur Inc.: Ossur is a world leader in orthotics and prosthetic limbs. The Biomechatronics Laboratory has ongoing collaborations with Ossur to translate our work to their range of assistive devices.
- Emotix: Emotix is a robotics company who has introduced a new range of social robots for home use. Our laboratory is working with them on innovative ways of advancing human-robot social interaction.
Robotic devices, safety in the home, independence, interactive device
Artificial intelligence (AI), robotic devices, patient-centred design
7. Key publications
Madgwick, S.O., Harrison, A.J. and Vaidyanathan, R., 2011, June. Estimation of IMU and MARG orientation using a gradient descent algorithm. In 2011 IEEE international conference on rehabilitation robotics (pp. 1-7). IEEE.
Boxerbaum, A.S., Werk, P., Quinn, R.D. and Vaidyanathan, R., 2005, July. Design of an autonomous amphibious robot for surf zone operation: part I mechanical design for multi-mode mobility. In Proceedings, 2005 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. (pp. 1459-1464). IEEE.
Bachmann, R.J., Boria, F.J., Vaidyanathan, R., Ifju, P.G. and Quinn, R.D., 2009. A biologically inspired micro-vehicle capable of aerial and terrestrial locomotion. Mechanism and Machine Theory, 44(3), pp.513-526.
Palmer, D., Kirschenbaum, M., Murton, J., Zajac, K., Kovacina, M. and Vaidyanathan, R., 2003, October. Decentralized cooperative auction for multiple agent task allocation using synchronized random number generators. In Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003)(Cat. No. 03CH37453) (Vol. 2, pp. 1963-1968). IEEE.
Kovacina, M.A., Palmer, D., Yang, G. and Vaidyanathan, R., 2002. Multi-agent algorithms for chemical cloud detection and mapping using unmanned air vehicles. ORBITAL RESEARCH INC CLEVELAND OH.