Devasena Pasupuleti
Osaka University, Systems Innovation, Graduate Student
- Amrita Vishwa Vidyapeetham, Amrita Multi Modal Applications Using Computer Human Interaction (AMMACHI) Labs, Graduate StudentAmrita Vishwa Vidyapeetham, Mechanical Engineering, Undergraduate, and 2 moreadd
- Devasena Pasupuleti is a Doctoral (PhD) scholar in Systems Science and Applied Informatics and a researcher at the Is... moreDevasena Pasupuleti is a Doctoral (PhD) scholar in Systems Science and Applied Informatics and a researcher at the Ishiguro lab, Osaka University, Japan. She served as a researcher at Ammachi Labs, the robotics and computer human interaction research center at Amrita University. She also worked as a Graduate Teaching Assistant at Amrita University. Her research interests range from human robot interaction including child robot interaction, social robots and cognitive robotics, to land and marine life conservation which she is passionate about. She has a Bachelors degree in Mechanical Engineering and a Masters degree in Robotics and Automation. She is seeking to find ways to apply robotics to device solutions for different communities and to design robotic games for children. She has a strong arts background with 15 years experience in the dance and music industry.edit
This study evaluates the effectiveness of child-robot interactions with the HaKsh-E social robot in India, examining both individual and group interaction settings. The research centers on game-based interactions designed to teach hand... more
This study evaluates the effectiveness of child-robot interactions with the HaKsh-E social robot in India, examining both individual and group interaction settings. The research centers on game-based interactions designed to teach hand hygiene to children aged 7-11. Utilizing video analysis, rubric assessments, and post-study questionnaires, the study gathered data from 36 participants. Findings indicate that children in both settings developed positive perceptions of the robot in terms of the robot's trustworthiness, closeness, and social support. The significant difference in the interaction level scores presented in the study suggests that group settings foster higher levels of interaction, potentially due to peer influence and collaborative dynamics. While both settings showed significant improvements in learning outcomes, the individual setting had more pronounced learning gains. This suggests that personal interactions with the robot might lead to deeper or more effective learning experiences. Consequently, this study concludes that individual interaction settings are more conducive for focused learning gains, while group settings enhance interaction and engagement.
Research Interests:
This paper presents a preliminary design and development of a novel wristband connected to a mobile application to enhance social interaction among children aged 7-12 years who struggle with expressing themselves in group settings.... more
This paper presents a preliminary design and development of a novel wristband connected to a mobile application to enhance social interaction among children aged 7-12 years who struggle with expressing themselves in group settings. Targeting pedagogical environments, the wristband can facilitate structured group discussions by allowing teachers to set parameters such as time limits via the app. Each child involved in the group discussion would wear an individual wristband, receiving notifications according to the set parameters. The system not only aids teachers in managing inclusive classroom discussions but also benefits parents by providing valuable insights into their child's social development. Moreover, it helps children build communication skills and confidence during group interactions. This innovative technology has the potential to positively impact educational settings by fostering inclusive happiness and a supportive environment for children's social and cognitive growth.
Research Interests:
We conducted an empirical study to co-design a social robot with children to bring about long-term behavioural changes. As a case study, we focused our efforts to create a social robot to promote handwashing in community settings while... more
We conducted an empirical study to co-design a social robot with children to bring about long-term behavioural changes. As a case study, we focused our efforts to create a social robot to promote handwashing in community settings while adhering to minimalistic design principles. Since cultural views influence design preferences and technology acceptance, we selected forty children from different socioeconomic backgrounds across India as informants for our design study. We asked the children to design paper mock-ups using pre-cut geometrical shapes to understand their mental models of such a robot. The children also shared their feedback on the eight resulting different conceptual designs of minimalistic caricatured social robots. Our findings show that children had varied expectations of the robot's emotional intelligence, interactions, and social roles even though it was being designed for a specific context of use. The children unequivocally liked and trusted anthropomorphized caricatured designs of everyday objects for the robot's morphology. Based on these findings, we present our recommendations for the physical and interaction features of a minimalist social robot assimilating the children's inputs and social robot design principles grounded in prior research. Future studies will examine the children's interactions with a built prototype. Keywords Child-robot interaction (CRI) • Social robot • Handwashing • Co-design • Human-robot interaction (HRI)
Research Interests:
Young children are at an increased risk of contracting contagious diseases such as COVID-19 due to improper hand hygiene. An autonomous social agent that observes children while handwashing and encourages good hand washing practices could... more
Young children are at an increased risk of contracting contagious diseases such as COVID-19 due to improper hand hygiene. An autonomous social agent that observes children while handwashing and encourages good hand washing practices could provide an opportunity for handwashing behavior to become a habit. In this article, we present a human action recognition system, which is part of the vision system of a social robot platform, to assist children in developing a correct handwashing technique. A modified convolution neural network (CNN) architecture with Channel Spatial Attention Bilinear Pooling (CSAB) frame, with a VGG-16 architecture as the backbone is trained and validated on an augmented dataset. The modified architecture generalizes well with an accuracy of 90% for the WHO-prescribed handwashing steps even in an unseen environment. Our findings indicate that the approach can recognize even subtle hand movements in the video and can be used for gesture detection and classification in social robotics.
Research Interests:
We present the design of a minimalist interactive social robot named Haksh-E which integrates audiovisual perception with artificial intelligence to nurture positive behaviors in children. We co-designed the robot's embodiment with... more
We present the design of a minimalist interactive social robot named Haksh-E which integrates audiovisual perception with artificial intelligence to nurture positive behaviors in children. We co-designed the robot's embodiment with children acting as design informants. The robot features expressive interactions, real time conversation and human action detection capabilities. Haksh-E can assist children in learning new behaviors as a tutor, play a supportive role in health interventions and also pose as an objective assessor of various indicators of health and hygiene. CCS CONCEPTS • Human-centered computing → HCI design and evaluation methods; Empirical studies in HCI ; Interaction design process and methods.
Research Interests:
This paper presents the design, implementation, and evaluation of a novel collaborative educational game titled "Land of Hands", involving children and a customized social robot that we designed (HakshE). Through this gaming platform, we... more
This paper presents the design, implementation, and evaluation of a novel collaborative educational game titled "Land of Hands", involving children and a customized social robot that we designed (HakshE). Through this gaming platform, we aim to teach proper hand hygiene practises to children and explore the extent of interactions that take place between a pro-social robot and children in such a setting. We blended gamification with Computers as Social Actors (CASA) paradigm to model the robot as a social actor or a fellow player in the game. The game was developed using Godot's 2D engine and Alice 3. In this study, 32 participants played the game online through a video teleconferencing platform Zoom. To understand the influence a pro-social robot's nudges has on children's interactions, we split our study into two conditions: With-Nudges and Without-Nudges. Detailed analysis of rubrics and video analyses of children's interactions show that our platform helped children learn good hand hygiene practises. We also found that using a pro-social robot creates enjoyable interactions and greater social engagement between the children and the robot although learning itself wasn't influenced by the pro-sociality of the robot.
Research Interests:
This dataset contains images and segmentation maps for sevenhandwashing steps, six of which are prescirbed WHO handwashing steps.This work is based on a sample handwashing video dataset uploadedby Kaggle userreal-timeAR... more
This dataset contains images and segmentation maps for sevenhandwashing steps, six of which are prescirbed WHO handwashing steps.This work is based on a sample handwashing video dataset uploadedby Kaggle userreal-timeAR (https://www.kaggle.com/realtimear) .Class-wise breakdown of samples---Step_1 : 8749Step_2 : 18725Step_3 : 7516Step_4 : 19926Step_5 : 18696Step_6 : 17274Step_7 : 16163------------------Total : 107049 images------------------
The demand for energy is increasing worldwide and the best way to meet this demand is a clean renewable energy source. Among the various options available solar energy can be considered as the best renewable energy source. This paper... more
The demand for energy is increasing worldwide and the best way to meet this demand is a clean renewable energy source. Among the various options available solar energy can be considered as the best renewable energy source. This paper deals with design, fabrication and performance study of a solar air heater coupled with evacuated tubes and heat pipes. Heat pipes are used to absorb the solar energy and evacuated tubes are used to prevent the convective losses. A selective absorber coating is used to coat the Inner side of the evacuated tube. Air is forced in to the duct of size 10cm x 10cm by a fan, which is driven by a photo voltaic panel. Six heat pipes and six evacuated tubes are used to absorb the solar radiation. A solar flux meter is used in to measure incoming solar radiation. Experiments are conducted with and without evacuated tubes. For both the configurations the variations of thermal efficiency with respect to time has been reported. The maximum thermal efficiency obtained is 35 % for evacuated tube with heat pipe. The average efficiency of evacuated tube with heat pipe is 1.5 times that of heat pipe alone.
Research Interests:
We present “Snowventure: Love’n’Learn”, an educational video game integrated with a virtual social robot, “CommU”, to improve the global self-esteem of elementary school children. CommU provides constant positive encouragement and... more
We present “Snowventure: Love’n’Learn”, an educational video game integrated with a virtual social robot, “CommU”, to improve the global self-esteem of elementary school children. CommU provides constant positive encouragement and motivation to children throughout the game, celebrating their small wins and losses, along with helping them solve certain levels in the game. We discuss in detail, the development of the game, along with the design of the behaviour and dialogues of virtual CommU. We then present the suggestions we received from children in India, aged 9 - 10 years, as part of our pilot trial study on how to improve upon our existing framework.
Research Interests:
This paper presents the preliminary design and development of a generalized Child-Robot-Interaction framework involving interactive game-play between the socially assistive robot NAO and children with varying types of dyslexia. Our... more
This paper presents the preliminary design and development of a generalized Child-Robot-Interaction framework involving interactive game-play between the socially assistive robot NAO and children with varying types of dyslexia. Our framework aims to enhance the learning and overall development of dyslexic children by integrating four vital modalities-auditory, visual and bodily kinaesthetic, reading and writing styles together into a set of four interactive games. These games, namely-Picture Memory (P), Sound and Read (S), Spelling (S) and Spatial (S) abbreviated as PSSS focus on aiding dyslexic children with their language skill sets such as reading, speaking, writing and listening, with the future goal being improving their mental well-being. Each of the games starts with the robot providing a set of instructions regarding the game to the child followed by the child playing the game with the robot. The PSSS games have been designed by taking prior literature and scientific data on child psychology, special education pedagogical methods, and linguistic studies into consideration. This research provides detailed experimental demonstrations of the design and working of the proposed framework. In the future, we intend to integrate the framework into real-time Human-Robot-Interaction studies to help children with special needs improve their mental health, confidence and ability to learn better.
Research Interests:
In this article, we present a proof of concept work for a Child-Robot Interaction (CRI) framework to help dyslexic children enhance their learning abilities. This is a preliminary study that focuses on providing aid with vital language... more
In this article, we present a proof of concept work for a Child-Robot Interaction (CRI) framework to help dyslexic children enhance their learning abilities. This is a preliminary study that focuses on providing aid with vital language skill sets by integrating four major learning styles namely, auditory, visual and bodily kin-aesthetic, reading, and writing styles. The CRI framework consists of four games, wherein in each game, the robot first provides instructions on how to play the game followed by the child and robot playing together to complete the game.