Unconventional sensing technology: enabling robots to operate autonomously in unknown environments

Teresa Vidal Callejo_Andy Roberts_3000xwim.jpg

Teresa Vidal Calleja teaches a robotic arm to pick up an object – the arm records the motion which can then be played back repetitively. Image courtesy of UTS by Andy Roberts.

Much of the world’s critical infrastructure is ageing and needs regular inspections and maintenance to prolong working life, increase resilience and minimise failures. Autonomous robots will play an increasingly important role in that process. Associate Professor Teresa Vidal Calleja has an ARC Discovery grant to work on sensors for the next generation of infrastructure robotics.

What is your expertise and why is it important in 2021?

I am an expert in robotics perception, giving robots the ability to perceive the world in which they operate and therefore make informed decisions about their tasks. My research focus is to enable robots to be deployed in environments that are either hazardous or with no human access, for example, in underground pipes, manufacturing plants, abattoirs, mines, disaster zones, inside bridges or outer space. This is particularly important in current times. For example, robots could be doing sanitation or delivery tasks without being at risk of catching a deadly virus.

Your new research project aims to aid robotics perception through the use of unconventional sensors. What does that involve?

The most common sensors in robotics measure distance and bearings to objects in the environment. These sensors are, for example, cameras or laser range finders. With distance information, a robot can localise within a known map, or build a map of the environment given its position and orientation at all times. It could also perform localisation and mapping concurrently to navigate unknown environments.

Our project focuses on a different type of sensor, what we call “unconventional sensors”. Examples of these sensors include magnetic, acoustic or event-based sensors. These unconventional sensors do not necessarily measure distance and/or bearings to objects in the environment. Therefore, it is not possible today to perform navigation tasks using this sensing technology. The main goal of my ARC discovery project is to develop the theory and algorithms to allow unconventional sensors to localise, map and characterise unknown environments.

What excites you about this research and who will benefit from it?

I’m excited about this project because it will allow us to explore new theoretical methods and develop novel algorithms to solve problems that are considered “solved” in robotics with existing technology. But they have never been tackled with what we call unconventional sensing technology. A solution to the localisation, mapping and characterisation problems with these type of sensors will enable robots to operate autonomously in environments that have not been possible today, for instance inside confined spaces requiring inspection.

We have the potential to improve the efficiency of critical infrastructure maintenance through faster, lower-cost, enhanced inspections, both helping infrastructure owners to improve maintenance efficiency and productivity, and reducing risks to public and workforce safety that are inherent when infrastructure is not adequately maintained.


NSSN_inverted_stacked.jpg

The NSW Smart Sensing Network (NSSN), an initiative of the NSW Government Office of the Chief Scientist and Engineer, is a consortium of eight leading universities across NSW and the ACT that brings together academia, industry and government to develop smart sensing solutions for complex challenges.

Working with the NSSN simplifies the process of engaging with universities by creating a single point-of-contact for the leading research suppliers in NSW.


Partner with us here.

Guest User