TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning
This addresses the need for accessible hardware to collect demonstration data for robot learning in domestic settings, though it is incremental as it builds on existing mobile manipulation designs.
The paper introduces TidyBot++, an open-source, inexpensive, and holonomic mobile manipulator designed to facilitate large-scale human-guided demonstrations for imitation learning in household tasks, and demonstrates that learned policies from collected data successfully perform various tasks.
Exploiting the promise of recent advances in imitation learning for mobile manipulation will require the collection of large numbers of human-guided demonstrations. This paper proposes an open-source design for an inexpensive, robust, and flexible mobile manipulator that can support arbitrary arms, enabling a wide range of real-world household mobile manipulation tasks. Crucially, our design uses powered casters to enable the mobile base to be fully holonomic, able to control all planar degrees of freedom independently and simultaneously. This feature makes the base more maneuverable and simplifies many mobile manipulation tasks, eliminating the kinematic constraints that create complex and time-consuming motions in nonholonomic bases. We equip our robot with an intuitive mobile phone teleoperation interface to enable easy data acquisition for imitation learning. In our experiments, we use this interface to collect data and show that the resulting learned policies can successfully perform a variety of common household mobile manipulation tasks.