Projects

The cornerstone of the QUT Centre for Robotics is that we are able to solve problems in a broad sphere of applications. Our research interests are diverse and we are continually in discussion with industry and government about how we can address their most pressing current and future challenges. Contact our team to discuss how we can collaborate with you.

 

COTSbot eliminating invasive reef species

COTSbot seeks out and controls the Great Barrier Reef's crown-of-thorns starfish (COTS), which are responsible for an estimated 40 per cent of the reef's total decline in coral cover.

When every second counts: Multi-drone navigation in GPS-denied environments

The aim of this research is to develop a framework for multiple Unmanned Aerial Vehicles (UAV), that balances information sharing, exploration, localization, mapping, and other planning objectives thus allowing a team of UAVs to navigate in complex environments in time critical situations.

Assessing the capabilities of digital imaging and Unmanned Aerial Systems (UAS) for species management

Logan, Tweed Shire and Gold Coast City Council

The key aim of this Project is to assess the utility of digital imaging for the cost effective detection and assessment of koala abundance in Tweed, Gold Coast and Logan local government areas (LGAs) using an innovative approach which combines Unmanned Aerial Vehicles, digital imaging, and statistical modelling.

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

Rheinmetall Defence Australia: Advanced Terrain Detection (ATD)

We're solving complex developmental problems related to autonomous driving, to help deliver game-changing autonomous vehicle technologies in Australia.

Contextual Hazard Detection

Mining3

In this project the team undertook a review and preliminary evaluation of existing technical solutions for hazard detection using vision sensors only.

Use of UAS and Hyperspectral Remote Sensing for Early detection of Phylloxera Infestation in Vineyards

The aim of this project is to use predictive models combined with high-resolution detection technologies to increase sampling efficiency and improve first detection rates.

Multiple Target Finding and Action Using Unmanned Aerial Systems

The ultimate aim of this project is to add real time weed management capabilities to low cost UAS for control of invasive species such as sphere thistle weed.

ACRV Picking Benchmark

There is an ongoing issue in research fields known as the reproducibility issue. Here, QUT researchers are fostering an important bench-marking system for robot pick and place research.

Deep Learning for Grasping and Manipulation

Deep learning has taken the research world by storm. At QUT, researchers are using advanced deep learning techniques in combination with established approaches to solve new problems.

Amazon Picking Challenge (2016)

At the 2016 Amazon Picking Challenge in Germany, 16 teams from around the world competed. The Australian Centre for Robotic Vision team reached sixth place in the picking task using a Rethink Robotics Baxter.

Developing pest risk models of Buffel Grass using Unmanned Aerial Systems and Statistical methods

Plant Biosecurity CRC

The aim of this project is to develop a system which combines new detection methods (UAVs and specialised sensors) with advanced modelling techniques to determine high-risk areas for pest risk surveillance, namely buffel grass.

Development and validation of a UAV based system for air pollution measurements

The aim of this research was to establish the best mounting point for four gas sensors and a Particle Number Concentration (PNC) monitor, onboard a hexacopter, so to develop a UAV system capable of measuring point source emissions.

A baseline dataset for performance evaluation of visual detection and classification techniques in mining environments

03/01/2018 - Ongoing

Mining3

This project aims at building a reference dataset to evaluate the performance of state-of-the-art visual-based object detection and classification methods in mining contexts

Aerial Manipulation for Remote Sensing Applications

This project aims to assess the use of aerial manipulation in remote sampling applications, and the capability of such systems in outdoor environments.

Detection and mapping of exotic weeds using UAS and machine learning: Bitou Bush Case Study

This project designed a system to detect bitou bush in coastal dunes using unmanned aircraft and machine learning classification algorithms towards the development of a flexible approach to monitoring and track similar weeds of interest in New South Wales and Queensland.

Automation-enabling positioning for underground mining

Advance Queensland Innovation Partnership, Caterpillar, Mining3

The project offers potential solutions to the challenge of accurately estimating the position of vehicles in underground mining environments.

HD maps for automated driving

13/07/2020 - 14/12/2020

A review on map creation, monitoring and maintenance to facilitate automated driving including government's potential role.

Semantic Mapping for Robotic Maintenance

12/01/2018 - 21/12/2020

Mining3

This project investigates the use of semantic mapping methods for the purpose of robotic maintenance in mining

Cameras and sensors

The system designed by the interdiscipliary robotics team combines advanced functionalities in pixel design to develop state-of-the-art miniaturised cameras for robotic vision.

UAVs with slung/swung loads

Much research has focused on standard multi-rotor position and attitude control with and without a slung load. However, predictive control schemes, such as Nonlinear Model Predictive Control (NMPC), have not yet been fully explored.

UAVs/ Drones for Agriculture and Plant Biosecurity

Plant Biosecurity CRC (2014 - 2018)

This project investigates the sensitivities and capacity of emerging unmanned aerial systems (UASs) and imaging technologies for biosecurity surveillance in viticulture, horticultural and grain industries.

Continuum robots

This project aims to develop highly dexterous snake-like tools for both manual and robotic orthopaedic surgeries by applying novel continuum mechanisms to the design and implementation.

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.

Reliability in Deep Machine Learning and Uncertainty for Object Detection

In order to fully integrate deep learning into robotics, it is important that deep learning systems can reliably estimate the uncertainty in their predictions. This would allow robots to treat a deep neural network like any other sensor, and use the established Bayesian techniques to fuse the network’s predictions with prior knowledge or other sensor measurements, or to accumulate information over time. Our work focusses on Bayesian Deep Learning approaches for the specific use case of object detection on a robot in open-set conditions.

Inference boats

The Inference boats are designed to be our eyes, ears and nose on waterways, 24 hours a day - rain, hail or cyclone.

Robotic knee arthroscopy

This project aims at developing a robotic surgical assistant for knee arthroscopy, composed of a robotic arm with an attached camera-arthroscope bundle for intra-articular navigation, and a robotic knee manipulator.

LunaRoo - A hopping Lunar science platform

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.

Amazon Picking Challenge (2017)

Our team came first in the global competition, against 16 teams from around the world competed, and winning the $80,000USD first prize. To do this, we created a novel Cartesian manipulator dubbed ‘Cartman’ with a rotating gripper to allow item pick-up using either suction or a simple two-finger grip.

Automated Early-Detection of the Invasive Grass African Lovegrass

This project is developing new techniques for automated early detection of the invasive grass African Lovegrass, using methods ranging from machine learning to psychophysics.

Establishing advanced networks for air quality sensing and analysis

This cross disciplinary project aims to develop, validate and implement novel methods for high sensitivity atmospheric sensing and apply cutting-edge statistical and analytic techniques to the data sets, unprecedented in scope and resolution.

Learning Robotic Navigation and Interaction from Object-based Semantic Maps

This project is supported by a 2019 Amazon Research Award to Assoc Prof Niko Suenderhauf.

This project investigates how such graph-based maps, containing both semantic and geometric information of objects in the environment, can be utilised to learn complex robotic tasks that require navigation, exploration, and interaction with the environment.

RangerBot

RangerBot is a low-cost, vision-enabled autonomous underwater vehicle for monitoring a wide range of issues facing coral reefs across the globe.

Navigating Under the Forest Canopy and in the Urban Jungle

01/01/2018 - 31/12/2020

ARC DP180102250

This Project aims to develop a framework for Unmanned Aerial Vehicles (UAV), which optimally balances localisation, mapping and other objectives in order to solve sequential decision tasks under map and pose uncertainty.

Visual Place Recognition for Robotics in Extreme Environments

This project is conducting research on visual place recognition for ground-based robots in extreme environments, such as underground mining and nuclear decommissioning scenarios.

[COMPLETED] How automated vehicles will interact with road infrastructure

QUT researchers who took an Artificial Intelligence (AI) system on a south-east Queensland road trip have identified the key role high-definition annotated maps will likely play in autonomous driving on Australian roads.

Scene Understanding and Semantic SLAM

We develop novel methods for Semantic Mapping and Semantic SLAM by combining object detection with simultaneous localisation and mapping (SLAM) techniques.

Unmanned Aerial Vehicles (UAVs) and artificial intelligence revolutionizing wildlife monitoring and conservation

The aim of this research is to explore and developed a system which includes thermal image acquisition as well as a video processing pipeline to perform object detection, classification and tracking of wildlife in forest or open areas.

AgBot II

Funded by Queensland Department of Agriculture and Fisheries

Meet AgBot II, a new generation tool for robotic site-specific crop and weed management.

Aerial Mapping of Forests Affected by Pathogens using UAVs, Hyperspectral Sensors and Artificial Intelligence: Myrtle Rust

This project aims to provide end-users with the value of these technologies in guiding decisions and adopting systems based on capabilities to detect exotic pathogens on host plantation and natural forests.

[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.

Mini Autonomous Vehicles

03/01/2017 - Ongoing

QUT has led development of a fleet of miniature autonomous vehicles as part of the Australian Centre for Robotic Vision.

Reinforcement Learning for Robot Navigation

The team investigate how classical navigation algorithms can be improved by learning-based approaches.

Semi-automated power pole inspection

We have developed an autonomy package to ensure that human-piloted inspection drones do not collide with poles, cross arms and wires.

Multi-UAV Navigation in GPS-Denied Environments under Location and Environmental Uncertainty

Th aim of this research is to develop a framework of a team of UAVs to cooperatively finding one or multiple targets in a real-world based environment with obstacles is being developed.

UAVs, Hyperspectral Remote Sensing and Machine learning Revolutionizing Reef Monitoring

The aim of this project is to predictive models and deep learning combined with high resolution hyperspectral detection technologies to increase surveying efficiency and to develop methodology for aerial coral bleaching detection.

UAV Navigation using semantic cues

25/02/2019 - Ongoing

This project aims to incorporate semantic cues into the navigation pipeline of UAVs. One of the projects key aspects is the influence of the unique positions of UAVs on the semantic information extracted from the vision system. Another key aspect is the transferral of algorithms to the constrained computing environment provided by UAVs.

Autonomous Robotic Platforms for Greenhouses

The goal of this project is to research and develop a fully autonomous robotic crop management system for protected cropping systems

Robotic Manipulation for Automated Maintenance

01/01/2019 - 21/12/2020

Mining3

The project evaluates the feasibility of current state-of-the-art robotic manipulation solutions to be applied to the task of automated vehicle maintenance

Autonomous UAV decision making under environment and target detection uncertainty

This project aims to investigate the incorporation of a sequential decision-making model framework for fully autonomous UAV operations, able to navigate under unstructured environments and reduce levels of target detection uncertainty.

Effect of lighting on visual odometry performance in underground mines

01/02/2017 - Ongoing

Mining3

This project evaluates the effect of illumination on the performance of Visual Odometry (VO) in underground mining environments to identify suitable illumination configurations that should be used to obtain the best performance of VO in these environments.

Antarctic Science for a Sustainable Future

Securing Antarctica’s Environmental Future (SAEF) is an Australian Research Council Special Research Initiative that aims to strengthen Antarctic science, policy and governance at a time of rapid environmental and geopolitical change.

Australian Research Council Industrial Transformation Training Centre for Joint Biomechanics

01/01/2020 - 02/08/2024

ARC INDUSTRIAL TRANSFORMATION AND TRAINING CENTRE FOR JOINT BIOMECHANICS INNOVATION FOR AUSTRALIAN BIOMECHANICAL RESEARCH The ARC ITTC for Joint Biomechanics aims to bring together leading researchers, industry partners and end-users to train a new generation of interdisciplinary and skilled graduates to tackle industry-focused challenges in joint biomechanics.

Moving to See

This project is investigating smarter ways for robots to see around all the clutter in order to better monitor crops in agricultural environments.

Novel autonomous robotic weed control to maximise agricultural productivity

Commonwealth Grant CRCPIX000099 (Cooperative Research Centre Project); Agent Oriented Software (Lead Partner)

The project aims to develop a robot to autonomously find and identify individual noxious weeds, spraying or using an alternative method to eliminate them. It will produce a series of operational prototypes ("Kelpie"), based upon a commercially available agricultural chassis.

Autonomous Mission Planning, Navigation and Geological Feature Recognition using UAVs (Drones)

22/07/2019 -

This research is aimed at developing a framework for mission planning and geological surface features detection using UAV in GPS-denied environments such as Mars. It involves the development and flight-testing of UAV prototypes capable of navigating in unknown GPS-denied environments in the search of geological features using on-board cameras.

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.

Surface Crack Detection and Localisation for Automated Underground Mine Void Characterisation

07/05/2018 - Ongoing

Mining3

This project focuses on the automatic detection of surface cracks (a.k.a fracture or sharp deformation breaks).

Monitor of pollutants adjacent to a motorway using Unmanned Aerial Vehicles

This project demonstrated that the PNC sampled with a constant traffic flow, increased from a concentration of 2×104 p/cm^3 near the ground up to 10 m, and then sharply decreased attaining a steady value of 4×103 p/cm^3 beyond a height of about 40 m.

Harvey – The Robotic Capsicum Harvester

QUT has developed a prototype robotic capsicum (sweet pepper) harvester nicknamed ‘Harvey’, combining robotic vision and automation expertise to benefit agricultural producers.

Robotic Vertical Farming Systems

This project aims to develop a robotic crop management system for the growth of nutrient-dense crops within Vertical Farming Systems