A5037037888- Robotics and Sensor-Based Localization
- Gaussian Processes and Bayesian Inference
- Advanced Image and Video Retrieval Techniques
- Robotic Path Planning Algorithms
- Optimization and Search Problems
- EEG and Brain-Computer Interfaces
- Smart Parking Systems Research
- Spectroscopy and Chemometric Analyses
- 3D Shape Modeling and Analysis
- Smart Agriculture and AI
- Control Systems and Identification
- Fractal and DNA sequence analysis
- Neural dynamics and brain function
- Advanced Neural Network Applications
- Machine Learning and Algorithms
- Indoor and Outdoor Localization Technologies
- Distributed Control Multi-Agent Systems
- Functional Brain Connectivity Studies
- Fault Detection and Control Systems
- Infrastructure Maintenance and Monitoring
Siemens (Germany)
2020
The University of Sydney
2015-2017
Australian Centre for Robotic Vision
2015-2017
This paper presents an extension of Gaussian process implicit surfaces (GPIS) by the introduction geometric object priors. The proposed method enhances probabilistic reconstruction objects from three-dimensional (3-D) pointcloud data, providing a rigorous way incorporating prior knowledge about expected in scene. key ideas, including systematic use surface normal information, are illustrated with one-dimensional and two-dimensional examples, then applied to simulated real data for 3-D...
We consider an optimal stopping formulation of the mission monitoring problem, in which a monitor vehicle must remain close proximity to autonomous robot that stochastically follows predicted trajectory. This problem arises diverse range scenarios, such as underwater vehicles supervised by surface vessels, pedestrians monitored aerial vehicles, and animals agricultural robots. The key characteristics we are stationary while observing robot, motion is modeled general stochastic process,...
This paper presents the Autonomous Siemens Tram that was publicly demonstrated in Potsdam, Germany during InnoTrans 2018 exhibition. The system built on a Combino tram and used multi-modal sensor suite to localize vehicle, detect respond traffic signals obstacles. An overview of hardware developed localization, signal handling, obstacle handling components is presented, along with summary their performance.
We consider an optimal stopping formulation of the mission monitoring problem, where a monitor vehicle must remain in close proximity to autonomous robot that stochastically follows pre-planned trajectory.This problem arises when underwater vehicles are monitored by surface vessels, and diverse range other scenarios.The key characteristics we stationary while observing robot, motion is modelled general as stochastic process.We propose resolution-complete algorithm for this runs polynomial...
Gaussian processes (GPs) enable a probabilistic approach to important estimation and classification tasks that arise in robotics applications. Meanwhile, most GP-based methods are often prohibitively slow, thereby posing substantial barrier practical Existing "sparse" speed up GPs seek either make the model more sparse, or find ways efficiently manage large covariance matrix. In this paper, we present an orthogonal memoises (i.e. reuses) previous computations GP inference. We demonstrate...