Taking social robot research into the wild
- Published on Monday, 19 March 2018 14:04
What happens when you take robotics research out of the lab and into a real life rural setting? What are the human perceptions of a water carrying robotic system? A team from the University of Glasgow and AMMACHI Labs at Amrita University in Kerala, India carried out a feasibility study with funding from Scottish Informatics and Computer Science Alliance (SICSA) and Amrita University, Kerala, India.
GCOSI asked Dr. Amol Deshmukh from the University of Glasgow about the background to the study and its outcomes, and Steven Kendrick from SICSA about how projects like this strengthen Scotland’s global reputation in computing research.
What is social robot research and what is unusual about taking social robot research ‘into the wild’?
Dr. Amol Deshmukh: “Social robot research is about studying how people interact with robots and how robots can influence human behaviour in certain situations. It is multi-disciplinary field with contributions from human–computer interaction, artificial intelligence, robotics, and social sciences. “Most robotics research is carried out in urban environments with people from developed countries. To the best of our knowledge this is the first robotics research study carried out in rural environment. Another thing that is unique about this study is it is making an effort to understand the challenges of introducing robotic solutions in a real life rural setting. This is an essential step towards informing design decisions for robotic products that seek to address the populations at the bottom of the economic pyramid. Robots in rural settings is a hugely unexplored research area where social robots could potentially be used to create a positive impact for the wider community rather than a privileged few in the developed world.”
Can you tell us about the location and people where you carried out your research. What are the daily challenges faced by participants?
Dr. Amol Deshmukh: “AMMACHI labs from Amrita University spend a significant amount of time with rural and tribal communities in order to understand their issues and nuances that often-times are not considered in technology design for such communities. They carry out community development activities in over 142 villages all over India. The study was conducted in collaboration with Amrita University in a rural village called Ayyampathy near Coimbatore in the southern Indian state of Tamil Nadu. The village consisted of 25 houses with approximately 200 inhabitants. We had 11 participants in the study and none of them had seen a robot before. Most of them hardly had any exposure to technology or basic education. Participants made an average of 15 trips daily carrying water jars (15-20 liters capacity) weighing up to 15-20kgs each from the water tank in their normal daily routine. The participants also expressed their discomfort while carrying water during the high heat of summer when the water availability is also limited. Thereby making our study a suitable use-case in this village's context.”
Can you outline the experiment and how it was conducted in the context of the rural setting?
Dr. Amol Deshmukh: “The study was conducted in November 2017 when the water availability from the nearby water tank (which is the main source of water supply in the village) is moderate during this time of the year. The water tank was at a distance of roughly 100 to 500 meters from the houses depending on how far the house was located. The study consisted of 11 participants, 10 females and 1 male, mean age 37, the youngest being 15 and the oldest 70. The participants were predominantly females as they are most likely to carry water for the house. None of them had ever seen a robot before, for all the participants it was their first time experience with a robot.
“The robot could speak in their local language and gave instructions to the participants step-by-step guiding them how to use the robot. When it was time to get water, the robot would wait its turn, and then the study participant would fill each jug and load it up. The robot would then politely ask, “Can you show me the way to your home so that I can bring water to your home?” Once there, the participant unloaded, emptied, and replaced the jugs, and the robot would say, ‘I hope I was helpful to you. Please remember to wash your hands before you eat.’"
Was there any resistance to participating and how was that overcome?
Dr. Amol Deshmukh: “Most subjects lived on a daily wage basis and had their own daily routine to carry out their household chores like cattle feeding, cooking, washing etc. They were not keen to commit a fixed time for the study. It was difficult to predict when they would need to fetch water. They had different water requirements and time schedule for fetching water. Some would do it early in the morning, others later during the day. It was challenging for researchers to be present with the robot when they required water.
“Approaching people to volunteer for the study was particularly challenging due to cultural constraints. The women in the village were hesitant to communicate initially with male researchers in our team. We had to recruit a female researcher to ease the flow of communication.”
What observations did you make about the impact the robot had on participants and what was their reaction to the technology?
Dr. Amol Deshmukh: “We used some questions from standard questionnaires used to study the effects of external factors on users' attitude, behavioural intention and actual use of technology. The robot's technological acceptance and social perception was very positive and we found a gender bias in terms of perception of the robot.”
Can this type of system provide a practical everyday solution for communities?
Dr. Amol Deshmukh: “More than 50% of population in India and the world does not have access to tap water at home and have to walk large distances daily to fetch and carry drinking water. This task is mostly performed by women who spend roughly 2-3 hours daily fetching water in rural India carrying pots or jars on their heads that weigh up to 20kgs when filled with water. This activity can lead to back, feet and posture problems. It also takes away a lot of time from their daily routine which can be used to perform other duties, make an income, child care, or in a younger girl's circumstance, be able to get a proper education.
“There are some villages in the desert areas of India where people have to walk 5 to 10 kilometers every day during summer to get water, in extreme heat. I think there is a lot of need there to provide technological interventions; the government is trying its best to provide water for them, but it’s not easy, so I think there is a lot of potential there for this technology to be impactful by carrying water for them.
“Also from such research, more people will take interest in working with the underserved populations in countries such as India where the people are hopeful of change and stand to gain a great deal from technological solutions to alleviate the drudgery from their daily lives.”
Dr. Amol Deshmukh: “I am very grateful to SICSA Postdoctoral and Early Career Researcher Exchanges (PECE) programme which provided me funding for me to travel to India and conduct this research. I also thank AMMACHI labs team for their collaboration and their access to rural communities. The feedback from this research has been really positive. We are exploring funding opportunities which is more substantial and looking for collaborations, if we get more funds, we could roll out more of these kinds of robots and carry out the research in a more extensive way.”
This research was carried out by Dr. Amol Deshmukh from University of Glasgow and Sooraj Krishna, Nagarajan Akshay, Vennila Vilvanathan, Sivaprasad J. V., and Rao R. Bhavani from Amrita University, Kerala, India. This research was funded by Scottish Informatics and Computer Science Alliance (SICSA) and Amrita University, Kerala, India.
Amrita University and its parent NGO led by world renowned humanitarian Amma, popularly known as the hugging saint, carry out community development activities in over 142 villages all over India. Researchers from its robotics and women empowerment research centre called Ammachi labs spend a significant amount of time with rural and tribal communities in order to understand their issues and nuances that often-times are not considered in technology design for such communities.
What drew SICSA to funding this project?
Steven Kendrick: “The SICSA Postdoctoral and Early Career Researcher Exchanges (PECE) programme provides funding for researchers to collaborate with Universities in the rest of Europe, North America, China and India. The aims of this programme are broadly two-fold: To provide career development opportunities for researchers working within Scotland; and to facilitate international collaborations involving Scottish Universities.
“There was overwhelming support from our independent reviewer panel and the SICSA Directors for funding this particular project. The study represents a fast-growing area of Computing research and it is extremely interesting because where we often see technology applied to urban environments and city dwellers, this research focuses on remote rural communities in developing countries (in this case, India). The application of this technology could potentially make a huge difference to those communities; and the project also demonstrated a good opportunity to study the interactions between those communities with the technology. It is of note that the technology is also transferable to other application domains, such as agriculture robots, where autonomous navigation and fetch and carry solutions can be used effectively.
“The project also represented a great opportunity for the University of Glasgow’s School of Computing Science to develop linkages AMMACHI Labs at Amrita University in India and both collaborators recently presented the study at the IEEE International Conference on Human-Robot Interaction 2018.”
How does this research impact on the global reputation of Scottish research?
Steven Kendrick: “Scotland has an excellent global reputation in Computing research and SICSA aims to maintain this by funding collaborative projects, events and other activities to support Scottish researchers in this exciting discipline. This study illustrates some of the fantastic work happening across Scotland in our Computing Departments – where technology is being applied to solve real-world problems. It is also great for us to see SICSA funded initiatives receive global recognition – the project was recently presented at the prestigious IEEE International Conference on Human-Robot Interaction 2018 – a clear measure of success for this particular research.”
Can you outline further opportunities for funding projects offered by SICSA
Steven Kendrick: “SICSA comprises all 14 Computing and Informatics Schools and Departments across the Scottish Higher Education sector and we deliver a lively programme of events and activities aimed at supporting Computing Science research and education. We also have funding available for all researchers in Computing and Informatics in Scotland. For full details of forthcoming events, please see http://www.sicsa.ac.uk/news-events/ and for a summary of our funding opportunities http://www.sicsa.ac.uk/funding/.”
Add a comment