Human-robot collaboration enables the synergistic cooperation between the precision, strength and repetitive capabilities of robots combined with the high-level intelligence and common sense of humans. This project hopes to improve the safety and efficacy of the construction industry through human-robot teaming. As a postdoctoral research fellow, my focus includes:

• Research into human activity recognition and intention prediction
• Developing demonstration platforms for conceptual robot human teaming tasks in the construction space
• Engaging with industry partners

A low cost fully autonomous AGV platform developed for the Department of Manufacturing and Industrial Engineering. My contribution to this project included being the lead project coordinator and software developer.

Video: https://www.youtube.com/watch?v=yaFYzCuyTzk&ab_channel=GihanLakmal

One serious facet of the worsening human-elephant conflict (HEC) in nations such as Sri Lanka involves elephant-train collisions. 

This work proposes leveraging recent developments in Convolutional Neural Network (CNN) technology to detect elephants using an RGB/infrared capable camera mounted on a train or near a known elephant crossing or hotspot. The CNN was trained using a curated dataset of elephants collected on field visits to elephant sanctuaries and wildlife parks in Sri Lanka. With this vision-based detection system at its core, a prototype unit of an early warning system was designed and tested.

Project partners include NVIDIA, IEEE SIGHT, UTS, University of Peradeniya and the Sri Lanka Railway Services.

My PhD research focused on adapting self-driving vehicle technology to personal mobility devices (PMDs) and delivery robots to improve their safety
and functionality. This has involved addressing the problem of vision-based localisation and SLAM in complex outdoor urban environments using
convolutional neural networks (CNNs). An autonomous mobility scooter platform was developed to showcase the capabilities of the proposed algorithms in a real-world scenario.

Video playlist of my research:

Playlist

Project Adithi is an attempt to combat period poverty in rural Sri Lanka through the development of a low-cost semi-automatic sanitary pad production machine. The machine is designed to be easy to operate so that women in rural communities can run and operate their own small-scale manufacturing. As head of Engineering at Arka Initiative, I project manage the design and development of the proposed machine.

This project is supported by the Arka Initiative (See Website https://www.arkainitiative.org/)