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

2026-03-09

AI Summary

This work proposes a low-cost, fully embedded dual-arm mobile manipulation platform based on XLeRobot to address the limited accessibility of such systems in research and education due to high costs and reliance on external computation. The platform integrates an NVIDIA Jetson Orin Nano as its main control unit, enabling untethered teleoperation, SLAM-based navigation, and GPU-accelerated vision-based manipulation without external dependencies. It features a lightweight yet high-stiffness mechanical structure and a Tri-Bus power topology that effectively isolates motor-induced electrical noise, ensuring system stability. With a total cost under $1,300, the platform is capable of performing complex mobile manipulation tasks autonomously, offering a cost-effective and self-contained experimental solution for robot learning.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Low Level & Physics-based Vision
• Natural Language Processing: Safety and Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• bimanual mobile manipulation
• low-cost robotics
• onboard compute
• untethered operation
• robot learning

Innovation

• bimanual mobile manipulation
• low-cost robotics
• embedded autonomy
• Tri-Bus power topology
• GPU-accelerated