Brain-Inspired Positioning for Fast, Energy-Efficient, Resilient Robotics

About the Fellowship

This project will develop the world’s first sub-millisecond, energy-efficient robot positioning system for reliable positioning in complex and resource-limited environments. It develops a novel brain-inspired approach where sensing and computation occur only when the scene changes, mirroring how neurons fire on meaningful events to maximise efficiency. By combining event-driven sensing with spectral processing, the system will achieve cooperative, ultra-low-latency positioning in challenging domains such as coral reefs, space, mine sites and defence.

The problem

Current localisation systems remain unreliable, slow and energy-intensive. Satellite navigation (e.g. GPS) fails underwater, indoors and in space, while camera- and LiDAR-based methods struggle under visual degradation, dust or intermittent communication. As a result, robots still cannot operate resiliently in the dynamic, remote environments where Australia most needs them: coral reefs, disaster zones, mine sites and future space missions.

The opportunity

Neuromorphic computing provides a new approach inspired by how the brain processes information: neurons activate only when something changes. Combined with event cameras, fast bio-inspired “silicon retinae” that detect changes in brightness rather than capturing full images, robots can sense motion and light variations in real time, processing only what changes instead of every frame.

Expected outcomes include new algorithms, open benchmarks, demonstrator platforms and a national roadmap, strengthening Australia’s capability in safe, low-emission, long-duration autonomy. PhD scholarships are available.