Trusted Autonomy

Impact

Trusted Autonomy is an emerging field of research focused on understanding and designing the interaction space between entities, each of which exhibits a level of autonomy. These entities can be humans, computer-controlled machines, or a mix of the two. Our aim is to integrate humans and machines seamlessly, naturally and efficiently to create a trusted and cooperative team to solve complex problems in an uncontrolled, uncertainty-rich environment. 

We have expertise in traditional machine learning, the navigation and control of autonomous vehicles, developmental robotics, computational motivation and computational red teaming. We are unique in Australia because of this mix of expertise. We have the ability to innovate concepts, taking them from ideation through to real-world applications that raise productivity, improve resources and enhance human safety. 

We have developed: 

  • more effective solutions to technological challenges including the deployment of autonomous vehicles, activities at the human-machine interface, high-fidelity military simulations and multi-robot operations in unknown and complex environments 
  • more agile and accurate decision-making cycles 
  • an accurate understanding of public acceptance and adoption rate of automation in everyday life 

Competitive Advantage

  • Unique combination of skills covering advanced topics such as robotics, AI, simulation and ethics 
  • Long-standing and deep ties with Defence 
  • Outstanding facilities for simulation and robotics 
  • Focus on trusted human-autonomy teaming 

Successful Applications

  • Swarm-based machine learning with knowledge sharing 
  • Demonstration of learning-to-fly from scratch on real unmanned aerial vehicles (UAVs) using neural networks and evolutionary fuzzy systems 
  • Demonstration of visual flight control of UAVs for flight in cluttered areas and landing on moving platforms 
  • Development of human performance surrogates for high-fidelity military simulations 
  • Hierarchical deep learning algorithms for robot control 
  • Trusted Human-Autonomy Teaming in Teleoperations 
  • Autonomous Learning, Reasoning and Decisions-Making in Dynamic Environments 
  • Behaviours Bootstrapping for Ad Hoc, Heterogeneous Robot Swarms 
  • Compliant Musculoskeletal Actuation in Flying Insects and Bio-inspired Designs for Miniature Robots 
  • Robust flight control systems for miniature lighter-than-air robots 
  • Autonomous Precision Access (APA): Resilient flight control for trusted, robust, real-time adaptive control using Neuro-Fuzzy approaches 
  • Heterogeneous Multi Robot Test Bench 
  • User-task co-adaptation for effective interactive simulation environments.