Superhuman place recognition with a unified model of human visual processing and rodent spatial memory

Project Overview

The main objective of any roboticist is to build robots that can do things in the world with precision and repetition, whether it be recognising the environment or moving around in it. One of the main trade-offs is the cost of the sensors used in doing this; The sensors that are being used in autonomous cars can costs tens of thousands of dollars, then there’s processing the data on top of that. So either we try to decrease the sensor costs by purchasing a lot of them, or we try to build better algorithms. Humans have about 21 billion neurons in their brains to process inputs and create understanding, whereas mice and rats range from 4 million to 18 million. by modelling how rats and mice behave, we will be able to create better algorithms to put on-top of existing cheap sensors.

Project Objectives

This project will revolutionize our understanding of how humans and animals use vision to determine their location in the world. This understanding will lead to new computer algorithms that enable robots to navigate in any environmental conditions using cheap visual sensors and breakthroughs in our knowledge of the brain.

 


Funding / Grants

  • Australian Research Council Future Fellowship Scheme FT140101229 (2015 - 2019)

Team


We model rat and other animal and human brains to create more intelligent robot navigation and perception systems.