Cutting the Cord: System Architecture for Low-Cost, GPU-Accelerated Bimanual Mobile Manipulation

TL;DR

This paper introduces a low-cost, GPU-accelerated bimanual mobile manipulator built on open-source hardware, featuring optimized design and embedded autonomy for versatile robotic tasks.

Contribution

It presents a novel, affordable mobile manipulation platform with integrated onboard compute, optimized mechanical design, and autonomous capabilities for research and education.

Findings

Built for under $1300 with onboard GPU computing.

Supports teleoperation, autonomous navigation, and vision-based manipulation.

Provides a low-cost alternative for robotics research and learning.

Abstract

We present a bimanual mobile manipulator built on the open-source XLeRobot with integrated onboard compute for less than \$1300. Key contributions include: (1) optimized mechanical design maximizing stiffness-to-weight ratio, (2) a Tri-Bus power topology isolating compute from motor-induced voltage transients, and (3) embedded autonomy using NVIDIA Jetson Orin Nano for untethered operation. The platform enables teleoperation, autonomous SLAM navigation, and vision-based manipulation without external dependencies, providing a low-cost alternative for research and education in robotics and robot learning.