Contact-rich manipulation remains a grand challenge for robotics; having dexterous manipulation capabilities that can automatically reason through contact with different objects and its body, as well as the surrounding environment, will widely broaden the spectrum of physical tasks we can automate in the world. Traditionally, model-based methods have tackled contact-rich manipulation by utilizing and studying the structure of contact models to come up with planning and control algorithms. In contrast, as we currently live through the era of deep learning, recent advances in learning have enabled entirely new capabilities and approaches for contact-rich manipulation as well. This shift of paradigm presents many interesting challenges and opportunities for the model-based manipulation community.
The objective of this workshop is to bring together researchers in the model-based manipulation community to present their work and review state-of-the art methods in the field. In conjunction, the workshop aims to facilitate discussions on the future of the field and ask several important questions: how can we synthesize model-based approaches and recent learning approaches into a coherent whole? Do we believe that there is structure we can leverage from the models that we use to better inform planning and control algorithms?
Participants are encouraged to ponder the following questions to get the discussion started (other questions related to the event’s overall theme are also welcome): 1) How can we synthesize model-based approaches and recent advances in learning into a coherent whole? 2) Do we believe that there is structure we can leverage from the models that we can use to better inform planning and control algorithms? 3) How can we bring together perception and model-based planning/control together?