Description

This workshop seeks to progress research in the topic of real-world manipulation and mobile manipulation, that is manipulators operating in environments which may be outdoors, naturally occurring, and unstructured. These real-world environments have unique characteristics making them non-trivial and difficult for robot operation compared to typical laboratory environments. Challenges include travelling over uneven and unpredictable terrain, working with deformable and non-rigid structures such as trees and other natural phenomena, and operating with high uncertainty due to environmental conditions.

This workshop aims to bring together researchers from diverse sub-communities within robotics including manipulation, mobile manipulation, field robotics, legged robotics, robot learning, SLAM, and robotic vision to discuss the following topics:

Is a benchmark or dataset required for progress in this area?
If so, should this be a real-world test environment, a high fidelity simulation, or low fidelity simulations with high domain randomisation etc.?
What gaps are holding outdoor and real-world mobile manipulation progress back from the rest of the manipulation field?
Is progress in this area going to be best achieved with data driven, analytic solutions, or a combined approach?
Why are manipulators slow and unsatisfying at completing tasks?
Mobile manipulators typically move in an unintuitive and unnatural manner, is this an issue for real-world environments?
What kind of sensing and contact models would be useful for environmental representation and mobile manipulation?
How do you handle uncertainty in real-world environments?
Are there specific challenges for long-term autonomy in the context of field robotics?
What is the role of human input in field mobile manipulation?