WAM07

Date: Wednesday, 27th June; Morning (1/2 day)

Workshop Aims

Deep learning is a rapidly advancing field in recent years, in terms of both methodological development and practical applications. It allows computational models of multiple processing layers to learn and represent data with multiple levels of abstraction. It is able to implicitly capture intricate structures of large-scale data and ideally suited to some of the hardware architectures that are currently available.

Whilst some of the technical challenges are still being addressed, including generative modelling, large-scale parameter optimisation, and handling heterogeneous multi-modal data with varying temporal dependencies and missing samples, its use for medical robotics has reached marked success. Examples include the use of deep learning for tissue characterisation, with which deep convolutional networks have dramatically improved the analysis performance compared to that of existing techniques. Other applications include surgical vision, navigation, learning, adaptation and task automation.

The purpose of this workshop is to report the latest advances in the field of deep learning for medical robotics, addressing both original algorithmic development and new applications of deep learning.

Topics to be covered

Topics for this special issue include, but are not limited to:

  • Deep learning for surgical vision and navigation
  • Deep learning for tissue characterization, optical biopsy and margin assessment
  • Deep learning for learning, adaptation and surgical task completion
  • Deep learning for human robot interaction and cooperative control
  • Non-linear dynamics with deep networks
  • Advanced manipulation and learning with deep networks
  • Control policies in dynamic environment
  • Dynamic active constraints and obstacle avoidance with deep networks
  • Interpreting and anticipating human actions with deep networks
  • High level task planning