Institution profile

Queensland University of Technology

Academic institutionaustralasia · au
Official website
Research library230linked papers
Opportunities0open roles
Selected work

Representative Papers

Long exposure localization in darkness using consumer cameras

May 06, 2013IEEE International Conference on Robotics and Automation

This work addresses the challenge of reliable visual localization using low-cost cameras under extremely low-light conditions—two orders of magnitude darker than standard benchmarks—where prolonged exposure and high ISO introduce severe motion blur, degrading conventional methods. We systematically evaluate SeqSLAM’s robustness under such extreme blur. Methodologically, we acquire usable grayscale images via long-exposure (132–10,000 ms) and high-gain imaging, and enhance SeqSLAM’s blur tolerance through block-wise and local-neighborhood normalization. We provide the first mechanistic insight into SeqSLAM’s effectiveness under strong motion blur and empirically validate its cross-illumination and cross-perceptual-domain generalization—e.g., daytime training to nighttime localization. Experiments demonstrate stable localization in both synthetic and real-world ultra-low-light scenarios. Statistical analysis confirms that normalization is critical for maintaining robustness against motion blur.

19 citationsRead paper

Sashimi-Bot: Autonomous Tri-manual Advanced Manipulation and Cutting of Deformable Objects

Nov 14, 2025

This work addresses the challenge of autonomous manipulation and high-precision cutting of natural, deformable 3D objects—exemplified by salmon fillets. Key difficulties include substantial inter-object geometric and dimensional variability, unknown viscoelastic material properties, and slippery, compliant surfaces prone to slippage. To overcome these, we propose a coordinated three-arm robotic framework integrating vision–tactile perception with deep reinforcement learning for real-time, adaptive in-hand tool manipulation and dynamic in-hand cutting. To our knowledge, this is the first system achieving stable multi-point grasping, deformation compensation, pose adjustment, and thin-slice cutting of soft-bodied targets via tri-arm coordination. Experiments demonstrate robust handling of highly heterogeneous salmon fillets, achieving sub-millimeter slicing accuracy; pick-up success rate and slice quality approach human-level performance. The framework establishes a scalable, generalizable paradigm for automated processing of deformable food products.

1 citations1 influentialRead paper

Flexible Transformations for Bayesian Score Calibration

Sep 04, 2026

Modern statistical models are growing increasingly complex in an effort to realistically capture system dynamics. Using standard simulation-based inference, these models may be computationally prohibitive, necessitating the use of model calibration methods. Bayesian score calibration is a computationally efficient framework for model calibration with strong theoretical guarantees. This framework learns an appropriate correction for an approximate model using a small number of simulations from the data-generating process. Currently, only a location-scale transformation has been explored, which may lack the flexibility to correct the complex error introduced by some approximate models. In this paper, we develop two flexible transformations for use in the Bayesian score calibration framework. The first is a polynomial extension, which can appropriately adjust approximate models with location-varying error. The second is a sequential application of Bayesian score calibration, which can accommodate approximate models with posteriors that have low support for the true parameter values. We also discuss an additional diagnostic for use with this framework. We demonstrate the increased flexibility these two approaches provide over Bayesian score calibration in two illustrative simulation studies.

0 citationsRead paper
Recent publications

Latest Papers

Flexible Transformations for Bayesian Score Calibration

Sep 04, 2026

Modern statistical models are growing increasingly complex in an effort to realistically capture system dynamics. Using standard simulation-based inference, these models may be computationally prohibitive, necessitating the use of model calibration methods. Bayesian score calibration is a computationally efficient framework for model calibration with strong theoretical guarantees. This framework learns an appropriate correction for an approximate model using a small number of simulations from the data-generating process. Currently, only a location-scale transformation has been explored, which may lack the flexibility to correct the complex error introduced by some approximate models. In this paper, we develop two flexible transformations for use in the Bayesian score calibration framework. The first is a polynomial extension, which can appropriately adjust approximate models with location-varying error. The second is a sequential application of Bayesian score calibration, which can accommodate approximate models with posteriors that have low support for the true parameter values. We also discuss an additional diagnostic for use with this framework. We demonstrate the increased flexibility these two approaches provide over Bayesian score calibration in two illustrative simulation studies.

0 citationsRead paper