Gordon Wyeth

Farmers are under growing pressure to increase production to feed a growing population, while at the same time considering environmental impact and constraints on land, water and labour. The increasingly larger farm machines cause significant soil compaction damage and are a single point of failure. Hence, in this project we developed the technology for small, inexpensive, cooperative robots for agriculture. This project was comprised of five themes: vision-based obstacle detection, vision-based [...]

The RoboRoos Robot Soccer team competed in the Small Size League of the annual RoboCup competitions. The goal of the RoboCup federation is "By the year 2050, develop a team of fully autonomous humanoid robots that can win against the human world soccer champion team."  The rules are similar to the human version of the game (FIFA), other than the elimination of the offside rule as well as modifications that accommodate [...]

This project is fast-tracking robotic technology for farms. Its purpose is to reinvigorate agriculture through increased production and reduced costs. Such technology can be used to conduct autonomous multi-vehicle operations in applications of weed management, fertilising, and seeding. The use of multiple, cost-effective field robots can enable alternative weed destruction methods such as mechanical, thermal or chemical. It can also enable autonomous methods for picking fruit and vegetables. The Strategic [...]

aka Robot Arm for Video Screen Manipulation The goal of the SAParm Project was to produce a proof-of-concept robotic video conferencing system to convey gestures of a remote conference participant. It could mimic human gestures such as nodding and shaking its head; show interest or strong feeling by moving forward; and indicate disinterest by moving backwards. It also moved in a very natural way by first turning its head, followed by [...]

Robots comprised of an omni directional drive system have a distinct kinematic and mobility advantage over the standard differential drive and Ackermann (car-like) drive. In this project we designed an omni directional drive robot with very high mobility that can negotiate typical edge and gap traversal obstacles in an indoor environment. It is based on a novel spherical drive mechanism which has the advantage of continuous contact with the ground plane to reduce [...]

Lingodroids are language learning robots that play games to construct shared lexicons. These fascinating mobile robots have learnt lexicons for places, distances, directions, and time. Our latest work demonstrates how to handle referential uncertainty, that is, how to resolve a word’s meaning between multiple candidates. Further, we have demonstrated language learning between robots that have different embodiment and cognitive capabilities. They differed in their sensors (camera images versus laser ranges); [...]

OpenRatSLAM, is an open-source C++ (ROS / OpenCV) and MATLAB version of RatSLAM. RatSLAM is a robot SLAM system based on the neural processes underlying navigation in the rodent brain, in particular the hippocampus.

My PhD thesis project was “Reading the Play – Adaptation by Prediction”.  The basis for the approach was akin to an elite sports player being able to "read the play", allowing for decisions to be made based on predictions of likely future outcomes. Using Markov chains we could model the opponent behaviour to prediction their likely future state. This brief video shows the prediction system at work in the RoboRoo robot [...]