Artificial Intelligence empowered robots for dexterous manipulation in warehouse automation

Start year: 2024

Summary: This project aims to develop intelligent warehouse robots capable of learning human-level dexterous manipulation of a wide variety of objects and adapting previous experience to new work tasks using reinforcement learning. Example tasks include picking and packing fragile objects, folding fabrics, and food harvesting in vertical farms. Due to high object and task variability encountered in warehouses, learning-based methods create new revolutionary opportunities. The Australian warehousing industry faces challenges with labour scarcity and a lack of automation with intelligent robotics. The Australian National Robotics Strategy states that robotics has the potential to add $170-600 billion per year to Australia’s GDP by 2030, address skill shortages and encourage employment growth[1]. Achieving this project’s research goals will put Australia at the forefront in adoption and utility of robotics in warehousing, leading to faster deliveries, better working conditions and a more efficient supply chain.

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.