Bio-inspired

Bio-Inspired Robotics

Rats are one of the animals that we are able to computationally simulate

Bio-inspired robotics is the process of using real world examples to create robots that have the same effect. This involves both the mechanical process of their body and their behaviour patterns. Some really good examples of bio-inspired robotics is Spot from Boston Dynamics. Where researchers have been modelling the dynamics of a cheetah and other four legged animals to try to recreate it to make a dynamic robot.

QUT leads a number of biologically-inspired robotics projects, ranging from modelling of the neural processes in animal and human brains underlying navigation, to modelling the behaviour of animals such as ants, rodents and birds in flight. By modelling these creatures, we are able to lead the way to better and more dynamic robots.

The projects are funded by the Australian Research Council, the Asian Office of Aerospace Research and Development (US Air Force) and Defence Science Technology Australia.

Projects

LunaRoo

03/01/2016 - 08/01/2019

LunaRoo was started as a proposal for the Lunar Payload Opportunity by the Google Lunar X Prize team scientists.

NeuroSLAM

Modelling the neural mechanisms in the brain underlying tasks like 3D navigation and 3D spatial cognition to develop new neuromorphic 3D SLAM and 3D cognitive navigation techniques.

US Air Force / AOARD: An infinitely scalable learning and recognition network

09/01/2016 - 09/01/2020

By creating better neural networks, we can ensure that we don't need massive amounts of data or computation to make robots

[COMPLETED] ARC Future Fellowship: Superhuman place recognition

01/06/2015 - 31/12/2019

Australian Research Council Future Fellowship Scheme FT140101229

By modelling the behaviour of rats, we can create better algorithms to make cheaper robots.

AUSMURI: Neuro-Autonomy: Neuroscience-Inspired Perception, Navigation, and Spatial Awareness for Autonomous Robots

09/01/2019 - 09/01/2024

State-of-the-art Autonomous Vehicles (AVs) are trained for specific, well-structured environments and, in general, would fail to operate in unstructured or novel settings. This project aims at developing next-generation AVs, capable of learning and on-the-fly adaptation to environmental novelty.