SAM: Species Assessment Mapper
SAM is an autonomous robotic system developed to patrol parks and natural reserves. Its primary goal is to detect and locate invasive species that pose a substantial threat to local biodiversity, such as the Zanzibar Yam. Currently, invasive species are monitored through a combination of active field surveys, legislation, public education campaigns and citizen science initiatives. SAM has the potential to help increase the efficiency and frequency of monitoring efforts across diverse ecosystems.
SAM leverages advanced technologies to enhance its functionality in monitoring invasive species. It utilises computer vision for the recognition and identification of these species within its environment. For geolocation, SAM employs the Global Navigation Satellite System (GNSS) to geotag the exact locations where invasive species are detected. Additionally, it is equipped with LiDAR technology to create detailed maps of its surroundings, aiding in navigation. The data collected, including species identification and geotagged locations, is transmitted in real-time to an online database. This information is accessible via a web application, enabling users to monitor the presence and spread of invasive species effectively.
By automating the detection and reporting process, SAM reduces the reliance on manual surveys by staff and volunteers, which are often time-consuming and labour-intensive. The provision of real-time data facilitates early intervention, crucial for preventing the spread of invasive species. This proactive approach can significantly cut down on potential surveillance costs and time required for eradication efforts, making the management process more cost-effective and efficient.

Project Team
Students:
- Adesara Kunjan Harshit (Mechanical Engineering, Class of 2026)
- Chu Wei Rong (Computer Science, Class of 2026)
- Devinaa Kumeresh (Engineering Science, Class of 2026)
- Jason Jonathan Tejaputra (Mechanical Engineering, Class of 2026)
- Nicholas Tan Yun Yu (Computer Engineering, Class of 2026)
Supervisors:
- A/Prof Lim Li Hong Idris (lhi.lim@nus.edu.sg)
- Dr Elliot Law (elliot.law@nus.edu.sg)
- Mr Graham Zhu (graham.zhu@nus.edu.sg)