Detecting kangaroos from autonomous vehicles using AI

Project Member(s): Ramp, D.

Funding or Partner Organisation: Conigital Pty Ltd (Conigital)
Conigital Pty Ltd (Conigital)

Start year: 2020

Summary: This project represents a collaboration with UK startup Conigital, who are partnering with Transport for NSW to develop autonomous vehicles in Australia. Our goal is to collaborate on one element of that - the detection of kangaroos. The three steps in the project are to (1) determine whether using a range of senses (radar, lidar, thermal, optical) can detect kangaroos from a moving vehicle, (2) predict the direction of movement of the kangaroo as the vehicle passes, and (3) to identify vehicle control measures that would reduce collision risk and improve safety. Initial funding will be provided to collect raw sensor data for aim (1). Over a few days, we will drive along roads where kangaroos are present, using a vehicle owned by Conigital and equiped with sensors. A Conigital employee will drive the vehicle, and one UTS staff member will provide direction on where and when to drive. Driving will take place in rural NSW, driving at two periods of the day (5-8pm; 5-8am). Driving will be conducted in accordance with road safety rules, UTS safety protocols, and Covid protocols. UTS OHS staff will be engaged with to ensure activities minimise risks to acceptable levels. UTS will participate in data analysis and on funding applications due in 2021. The ACEC will be engaged with to determine whether animal ethics will be necessary.

FOR Codes: Animal behaviour, Image processing, Road Safety

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.