Lifelong robotic navigation using visual perception. Service robots are becoming a major part of our working and personal environments, in much the same way as personal computers already have. This project will develop new methods of practical and useful robot navigation that will enable Australia's industries and services to remain internationally competitive.
Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently ....Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently learn complex interaction and navigation behaviours that transfer to unseen environments. Our research should benefit new applications in domains of economic and societal importance that are currently too complex, unsafe, and uncertain for robot assistants, such as aged care, advanced manufacturing and domestic robotics.Read moreRead less
Talking with Robots: Evolving Grounded Language for Embodied Agents. The coming personal robot revolution will be built on robots that have real-world intelligence, with an ability to understand and communicate about the world in the way we humans do. This project extends a previous ARC project, which developed robot-friendly languages for naming places in the world. This new project will develop the robots' abilities and language to understand a comprehensive range of real world objects, places ....Talking with Robots: Evolving Grounded Language for Embodied Agents. The coming personal robot revolution will be built on robots that have real-world intelligence, with an ability to understand and communicate about the world in the way we humans do. This project extends a previous ARC project, which developed robot-friendly languages for naming places in the world. This new project will develop the robots' abilities and language to understand a comprehensive range of real world objects, places, actions, attributes and relationships. This project represents a major advance for Australia in the new and fast growing personal robot industry.Read moreRead less
Enhancing Intelligent Robot Navigation with the Evolution of a Robot-Friendly Language. Personal robots are set to become as popular as personal computers. The key ingredient that has been missing is intelligence - not the kind of intelligence that plays chess, but the kind that allows robots to understand the world in the way that we humans do. This project represents a major advance in that kind of intelligence, giving robots the ability to understand the world and the ability to communicate a ....Enhancing Intelligent Robot Navigation with the Evolution of a Robot-Friendly Language. Personal robots are set to become as popular as personal computers. The key ingredient that has been missing is intelligence - not the kind of intelligence that plays chess, but the kind that allows robots to understand the world in the way that we humans do. This project represents a major advance in that kind of intelligence, giving robots the ability to understand the world and the ability to communicate about their experiences. Armed with this new technology, Australia will have a competitive edge in the new and fast growing personal robot industry.Read moreRead less
Robot Navigation From Nature: Simultaneous Localisation And Mapping Based On Hippocampal Models. This project will create a new method of robot control that allows a robot to learn a map of any area and then navigate using that map. The new method is based on ideas from recent models of rodent brains.
The resulting improvements in robot navigation offer immediate benefits to the emerging service robot industry. In addition, the act of reproducing a high-level brain function in a robot will inc ....Robot Navigation From Nature: Simultaneous Localisation And Mapping Based On Hippocampal Models. This project will create a new method of robot control that allows a robot to learn a map of any area and then navigate using that map. The new method is based on ideas from recent models of rodent brains.
The resulting improvements in robot navigation offer immediate benefits to the emerging service robot industry. In addition, the act of reproducing a high-level brain function in a robot will increase the understanding of memory and learning in mammals, including humans. Consequently, the outcomes of this research will benefit both robot designers and brain researchers.
Read moreRead less
Assuring dependability of complex adaptive multi-agent systems using time bands. As the complexity of computer-based systems rapidly increases, we need new methods for assuring their correct behaviour. This project will provide a means of relating behaviour at different timescales, enabling us to understand how the long-term behaviour of a system results from the short-term interactions between its components.
Brain-based sensor fusion for navigating robots. This project uses new findings in neuroscience to create robots that can self-determine which of their sensors will best help them learn to navigate in an environment. This technology enables robot systems to be flexibly deployed without prior calibration for wide ranging applications in environments from office buildings to outdoor ecosystems.
Real-time high-level cognitive robotics controllers. Technological advances have seen the recent release of commercially affordable mobile robots. In the wake of Sony's immensely successful AIBO entertainment robot, it is anticipated that the market will be flooded with similar devices in short time. However, while traditional robotics focuses on problems like navigation and sensory perception, scant attention has been paid to the development of high-level cognitive robotics languages for coordi ....Real-time high-level cognitive robotics controllers. Technological advances have seen the recent release of commercially affordable mobile robots. In the wake of Sony's immensely successful AIBO entertainment robot, it is anticipated that the market will be flooded with similar devices in short time. However, while traditional robotics focuses on problems like navigation and sensory perception, scant attention has been paid to the development of high-level cognitive robotics languages for coordinating these lower-level "skills". Such languages allow development of sophisticated robot controllers. We aim to develop a cognitive robotics language capable of controlling robots in real-time and in a multi-agent setting requiring coordination among agents.Read moreRead less
Human Cues for Robot Navigation. The world has many navigational cues for the benefit of humans: sign posts, maps and the wealth of information on the internet. Yet, to date, robotic navigation has made little use of this abundant symbolic information as a resource. This project will develop a robot navigation system that can navigate using information beyond the robot's range sensors by incorporating knowledge gained by reading room labels, following human route directions or interpreting maps ....Human Cues for Robot Navigation. The world has many navigational cues for the benefit of humans: sign posts, maps and the wealth of information on the internet. Yet, to date, robotic navigation has made little use of this abundant symbolic information as a resource. This project will develop a robot navigation system that can navigate using information beyond the robot's range sensors by incorporating knowledge gained by reading room labels, following human route directions or interpreting maps found on the web. This project will demonstrate the robot's navigation ability by comparing its performance with a human as it learns to find its way around campus by asking for directions, reading signs and maps, and searching the internet for clues.Read moreRead less
Automated benthic understanding with multimodal observations. This project aims to deliver cost-effective techniques to explore and monitor marine environments. The project will develop novel methods for classification of large extent, multimodality seafloor surveys consisting of high-resolution visual 3D gigamosaics made of tens of thousands of images coregistered with broad-scale, lower resolution remote sensing data. This knowledge is essential for designing cost-effective, scalable systems t ....Automated benthic understanding with multimodal observations. This project aims to deliver cost-effective techniques to explore and monitor marine environments. The project will develop novel methods for classification of large extent, multimodality seafloor surveys consisting of high-resolution visual 3D gigamosaics made of tens of thousands of images coregistered with broad-scale, lower resolution remote sensing data. This knowledge is essential for designing cost-effective, scalable systems to explore, map and monitor Australia's marine environments. At a broader level, the approach and the techniques developed in this project have the potential to have applications in other areas such as terrestrial and intertidal ecology, extending positive impacts beyond benthic environments.Read moreRead less