Profile picture

A/Prof Tobias Fischer

Associate Professor, ARC DECRA Fellow, ARC Future Fellow (from 2027) and Chief Investigator
Queensland University of Technology
I am an Associate Professor and ARC DECRA Fellow at the Queensland University of Technology, and have been awarded a $1.1M ARC Future Fellowship commencing in November 2027. My research focuses on robot localisation and underwater perception, blending neuroscience and robotics to push the boundaries of intelligent systems operating under resource constraints. To date, I have secured over $5M in competitive funding and currently serve as Chief Investigator of the $1.3M Reef Restoration and Adaptation Program and the $700k Queensland Quantum Technologies Talent Building Program, with previous grants from Intel Labs and Amazon. After obtaining my PhD from Imperial College, I have published over 50 papers in prestigious venues including Science Robotics, PAMI, TRO, CVPR, ECCV, ICCV, IJCAI, ICRA, and IROS. Recognition for this work includes the UK Best PhD in Robotics Award and several best paper and best poster awards. I serve as an Area Chair / Associate Editor for leading conferences (ICRA/IROS/RSS) and journals (RAL). As co-chair of the IEEE-RAS Women in Engineering Committee, I actively promote gender diversity in STEM. My PhD students have gone on to successful careers as Assistant Professor, Research Scientists, and Research Fellows.
Contact Me:  
tobias.fischer@qut.edu.au

News

  • Preprint
    Two new event-camera preprints led by Adam Hines: the open-source EventCV library for event-based robotic vision, and MegaEvent for multi-viewpoint geo-localization.
  • Paper
    Accepted to WACV 2027: Why Domain Matters, domain-aware benchmarking of underwater object detection and annotation quality, led by PhD student Melanie Wille.
  • Talk
    Three talks at the ADSTAR Summit 2026 on assured positioning without GPS: latency-driven visual positioning, neuromorphic positioning for energy-efficient autonomy, and neuromorphic and quantum sensing for underwater positioning.
  • Award
    Promoted to Associate Professor at the Queensland University of Technology, effective 1 August 2026.
  • Preprint
    New preprint: TACO, a test-and-check framework for robust pose graph optimization, led by postdoc Emilio Olivastri.
  • Paper
    Published in the International Journal of Hydrogen Energy: time-resolved oxygen bubble dynamics in proton exchange membrane electrolysers.
  • Paper
    Presented at ICUAS 2026: aerial visual place recognition in Antarctica for robust monitoring in extreme environments.
  • Talk
    At ICRA 2026: a keynote tutorial with Peter Corke, From Research Code to Running Systems (video below), workshop talks on low-latency neuromorphic localization and underwater robotic vision for reef restoration, and three papers on sub-millisecond event-based place recognition, Event-LAB and coral spawn monitoring.
  • Preprint
    New preprint: DisPlace, discriminative place projections for multi-reference visual place recognition, led by PhD student Dhyey Manish Rajani.
  • Paper
    Published in IEEE Robotics and Automation Practice: open-source, cost-aware kinematically feasible planning for mobile and surface robotics, the planner behind Nav2’s Smac Planner.

Featured Videos

ICRA 2026 Keynote Tutorial – From Research Code to Running Systems

My part of the ICRA 2026 keynote tutorial with Peter Corke on modern robotics software. Through live coding, I show how Pixi and the conda-forge ecosystem let ROS and PyTorch be composed into portable, reproducible workflows that run across platforms, from phones and the browser to high-performance computing, enabling large-scale benchmarking of applications such as SLAM. Tutorial materials.

ICRA 2025 Keynote – Visual Place Recognition

My ICRA 2025 keynote explores Visual Place Recognition (VPR) using bio-inspired, low-power sensing. I discuss neuromorphic event-based cameras, spiking models for localisation, and coral-reef applications within the Reef Restoration and Adaptation Program.

How Robots Navigate Without GPS Using Vision

A one-minute public-facing video explaining how robots use only visual cues to navigate in GPS-denied environments such as indoors, underground, and underwater. Read the article.

Robotic Vision That Works in the Real World

My talk at the MIT Robotics Worldwide Workshop covers neuromorphic place recognition, underwater perception for reef restoration, and open-source robotics tools such as RoboStack and ROS2WASM. I discuss how neuromorphic computing enables robust operation where GPU-based methods are impractical.