TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning

TL;DR

This work tackles the data bottleneck in robot learning for mobile manipulation by introducing TidyBot++, an open-source holonomic mobile base built from affordable parts that can independently control $(x, y, \theta)$. It pairs the base with a WebXR-enabled mobile-phone teleoperation interface to facilitate intuitive, scalable data collection for imitation learning and demonstrates diffusion-policy training across real household tasks. Results show high task success rates and clearer, more efficient trajectories when using a holonomic base compared to a nonholonomic differential drive, underscoring the practical benefits for real-world data collection and policy learning. By releasing hardware designs, control code, and documentation openly, the work aims to democratize access to high-mobility mobile manipulators and accelerate research in robot learning.

Abstract

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.

Figures (5)

• Figure 1: We develop an open-source mobile manipulator with a holonomic base (left), and show that it can perform a variety of household tasks in a real apartment home (right).
• Figure 2: A simplified illustration of caster wheels on a holonomic base.
• Figure 3: Our mobile base is designed to be modular and easily reconfigurable. It has very few components and can be assembled in 1 to 2 days.
• Figure 4: Isometric and top views of a simplified caster, showing the caster offsets $b_x$ and $b_y$, wheel radius $r$, steer and roll joints $\phi$ and $\rho$, and caster module placement $(h, \beta)$ from the base origin.
• Figure 5: In the wipe countertop task, the differential drive robot is forced to take a less efficient path as it is subject to nonholonomic constraints.