Meet
Dr Xing Wang is currently a Lecturer in Robotics Engineering at the University of Canberra, where his research focuses on agricultural robotics, soft robotics, and the integration of robotic manipulation with machine learning-based perception systems.
Prior to this role, Dr Wang was a Postdoctoral Research Fellow at CSIRO Robotics, Data61 (2022 – 2024), where he worked on computational design methods for soft robotics, contributing to both the theoretical and applied advancements in adaptive and compliant robotic systems.
Dr Wang is also one of the four key inventors of the Monash Apple Retrieving System (MARS), an autonomous apple-harvesting robot designed for real-world agricultural deployment. The system was awarded a provisional Australian patent AU 2021904217 and has been widely recognised in the field of agri-tech, featured in over 50 national and international media outlets, including BBC News and ABC News. MARS was also demonstrated at Agriculture Victoria’s Tatura Smart Farm in March 2022.
Dr Wang holds a PhD in Robotics from Monash University, which he completed in 2022 with an “Excellent” grade in the thesis examination. He also holds a Bachelor of Engineering (First Class Honours) from Monash University (2018), as well as a Bachelor of Mechanical Engineering from Central South University (China), completed through a 2+2 joint program.
Damith HerathIn Australia, an alarming 75.8 million tonnes of waste is generated annually, with organic waste contributing approximately 14.4 million tonnes. Food waste, a major component of organic waste, accounts for 32.6% and is predominantly disposed of in landfills, where it generates methane, a greenhouse gas with a global warming potential at least 28 times higher than carbon dioxide.
Organic waste management is a crucial component of a circular economy, which prioritizes reducing waste through the reuse and recycling of products and materials. It is a tedious and complicated task, largely accomplished through manual labor. We introduce a novel ‘in-the-wild’ multimodal image dataset of 15-band NIR multi-spectral and single band thermal images of bulk food waste in an industrial setting. The dataset showcases a number of complex computer vision problems that are unavoidable constraints in this setting. Benchmarking against different computer vision algorithms is performed to highlight these challenges. The key issues and their place in robotic waste processing for industrial applications, and grand challenge objectives are discussed.
