Adaptive and Efficient Robot Positioning Through Model and Task Fusion

About the Fellowship

This project aims to create fit-for-purpose positioning systems that continuously adapt to diverse and changing environments. The project expects to contribute to the knowledge across robotics, computer vision and neuromorphic computing. Expected outcomes include ground-breaking place recognition techniques that address two fundamental limitations in the state of the art: continuous adaptation, critically important in safety-critical systems, and energy efficiency, critically important in resource-constrained systems.

Why it matters

When robots localise visually, the problem is often called visual place recognition (VPR). Crucially, VPR enables navigation and decision-making without risky dependence on satellites, which are unavailable indoors, unreliable in built-up areas, and over which Australia has no control. The Fellowship addresses three shortcomings of current VPR systems:

1. Current VPR systems are “one size fits all”. They do not adapt well to changing environments, like transitioning from rural to urban areas.
2. VPR algorithms do not exploit complementary information from non-positioning tasks that operate in parallel, like object detection and semantic segmentation.
3. There is a heavy focus on conventional computing, raising questions about long-term sustainability, data privacy and ever-increasing power consumption. Neuromorphic computing provides a viable alternative for low-power edge devices.

This should provide significant benefits, such as accelerated deployment of mobile robots, drones and augmented reality solutions in manufacturing, defence, healthcare, households and space.