Automation-enabling positioning for underground mining
The mining industry is changing as the industry is becoming increasingly competitive. To keep pricing low, mining companies have been turning to advanced technology to keep up. As well as the increase in efficiency, companies are also looking to ensure that safety is at the top priority, and that involves ensuring any collapses are able to be localised as quick as possible. QUT, Mining3 and Caterpillar have signed a collaborative agreement for the research and development of a new positioning system for underground mining. The project formally commenced in March 2017, and with financial support from the Queensland Government as part of its Advance Queensland Innovation Partnerships program, the project offers potential solutions to the challenge of accurately estimating the position of vehicles in underground mining environments.
The intended outcome of the research project is a cost-effective, reliable, camera-based positioning system for locating and tracking underground mining vehicles within one metre of accuracy; as well as a sophisticated, multi-sensor system that provides centimetre-accurate positioning which will ultimately enable the automation of mine vehicles. Essentially it delivers the equivalent of GPS to underground mining, without the requirement for significant infrastructure installed throughout the mine.
This exciting new research will have a major impact on the global mining industry, dramatically improving existing mining operations and facilitating automation in underground environments.
- F Zeng, A Jacobson, D Smith, N Boswell, T Peynot, M Milford, “LookUP: Vision-Only Real-Time Precise Underground Localisation for Autonomous Mining Vehicles“, in IEEE International Conference on Robotics and Automation, 2019.
- Zeng, Fan, Jacobson, Adam, Smith, David, Boswell, Nigel, Peynot, Thierry, & Milford, Michael (2019) TIMTAM: Tunnel-image texturally accorded mosaic for location refinement of underground vehicles with a single camera. IEEE Robotics and Automation Letters, 4(4), Article number: 8784227 4362-4369.
- Zeng, Fan, Jacobson, Adam, Smith, David, Boswell, Nigel, Peynot, Thierry, & Milford, Michael (2018) I2-S2: Intra-image-SeqSLAM for more accurate vision-based localisation in underground mines. In Woodhead, I (Ed.) Proceedings of the Australasian Conference on Robotics and Automation (ACRA) 2018. Australian Robotics and Automation Association (ARAA), Australia, pp. 1-10.
- Jacobson, Adam, Zeng, Fan, Smith, David, Boswell, Nigel, Peynot, Thierry, & Milford, Michael (2018) Semi-supervised SLAM: Leveraging low-cost sensors on underground autonomous vehicles for position tracking. In Laschi, C (Ed.) Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, United States of America, pp. 3970-3977.
- Zeng, Fan, Jacobson, Adam, Smith, David, Boswell, Nigel, Peynot, Thierry, & Milford, Michael (2017) Enhancing underground visual place recognition with Shannon Entropy saliency. In Kodagoda, S, Alempijevic, A, & Vidal Calleja T, T (Eds.) Proceedings of the Australasian Conference on Robotics and Automation 2017. Australian Robotics and Automation Association, Australia, pp. 1-10.
Funding / Grants
- Advance Queensland Innovation Partnership, Caterpillar, Mining3 (2017 - 2019)
Other Team Members
- Richard Gogolin
- Adam Jacobson (formerly at QUT)
- Nigel Boswell (now at FMG)
- David Smith (now at FMG)
- David Pappin
- Chris Taylor
- Professor Paul Lever
- Dr Ewan Sellers
- Maciej Matuszak
- Umesh Mutubandara (also former QUT, now at Rheinmetall Germany)
- Alice Lam (also QUT)