This talk presents advances in autonomous drone decision-making and control using machine learning, focusing on single-drone control and multi-drone coordination.

Modular reconfigurable systems are key for space robotics and these systems need decentralized, adaptable communication protocols that work across physical and protocol levels and integrate new components.

Dr Calum Imrie will give an overview about the practicalities of deploying autonomous systems

Dr. Hyung Jin Chang will present his research on human-centred visual learning, the primary goal is to create vision-based algorithms that prioritise the usability and usefulness of AI systems by addressing human needs and requirements.

Dr Edward Johns will present his research from the past year in his lab which aims towards more practical robot learning without huge data requirements.

Professor Mehmet Dogar will present their work on robotic object manipulation, particularly, robot motion planners and controllers that use predictions about the motion of contacted objects.

Dr Babar Jamil will present the work in designing new robotic systems that share the physical features of soft and rigid structures, thereby, taking advantage of compliance of soft actuation and accuracy of rigid structures.