SuperSuit: An Isomorphic Bimodal Interface for Scalable Mobile Manipulation

TL;DR

SuperSuit introduces a bimodal data collection framework for mobile manipulators, enabling scalable, high-quality demonstrations through shared kinematic interfaces that improve data throughput and policy performance.

Contribution

It presents a novel isomorphic bimodal interface for mobile manipulation that unifies teleoperation and active demonstration, facilitating scalable data collection without modifying downstream policies.

Findings

2.6× higher demonstration throughput in active mode

Comparable policy performance with different data sources

Performance improves with increased active demonstration volume

Abstract

High-quality, long-horizon demonstrations are essential for embodied AI, yet acquiring such data for tightly coupled wheeled mobile manipulators remains a fundamental bottleneck. Unlike fixed-base systems, mobile manipulators require continuous coordination between $SE(2)$ locomotion and precise manipulation, exposing limitations in existing teleoperation and wearable interfaces. We present \textbf{SuperSuit}, a bimodal data acquisition framework that supports both robot-in-the-loop teleoperation and active demonstration under a shared kinematic interface. Both modalities produce structurally identical joint-space trajectories, enabling direct data mixing without modifying downstream policies. For locomotion, SuperSuit maps natural human stepping to continuous planar base velocities, eliminating discrete command switches. For manipulation, it employs a strictly isomorphic wearable arm in both modes, while policy training is formulated in a shift-invariant delta-joint representation to mitigate calibration offsets and structural compliance without inverse kinematics. Real-world experiments on long-horizon mobile manipulation tasks show 2.6$\times$ higher demonstration throughput in active mode compared to a teleoperation baseline, comparable policy performance when substituting teleoperation data with active demonstrations at fixed dataset size, and monotonic performance improvement as active data volume increases. These results indicate that consistent kinematic representations across collection modalities enable scalable data acquisition for long-horizon mobile manipulation.