AhaRobot: A Low-Cost Open-Source Bimanual Mobile Manipulator for Embodied AI

TL;DR

AhaRobot tackles the barrier of expensive, limited open-world mobile manipulation by delivering a $1,000 hardware, fully open-source dual-arm mobile robot with a belt-driven lifting mechanism, horizontal SCARA-like arms, and a differential base. It pairs this hardware with a dual-motor backlash elimination and stiction-compensation control scheme, and introduces RoboPilot, a $50 remote teleoperation solution using 26-faced markers for precise 6-DoF control via a web interface. The system enables fully remote, long-horizon data collection and supports autonomous learning through imitation learning, achieving solid performance in simple tasks and demonstrating clear advantages in data collection efficiency (≈30% faster) and remote operation across complex tasks. The work emphasizes accessibility and openness to accelerate embodied AI research, while acknowledging limitations such as lack of collision sensing and potential teleoperation delays in vision-based interfaces. Overall, AhaRobot provides a practical, scalable platform for advancing real-world embodied AI with open hardware and software.

Abstract

Navigation and manipulation in open-world environments remain unsolved challenges in the Embodied AI. The high cost of commercial mobile manipulation robots significantly limits research in real-world scenes. To address this issue, we propose AhaRobot, a low-cost and fully open-source dual-arm mobile manipulation robot system with a hardware cost of only $1,000 (excluding optional computational resources), which is less than 1/15 of the cost of popular mobile robots. The AhaRobot system consists of three components: (1) a novel low-cost hardware architecture primarily composed of off-the-shelf components, (2) an optimized control solution to enhance operational precision integrating dual-motor backlash control and static friction compensation, and (3) a simple remote teleoperation method RoboPilot. We use handles to control the dual arms and pedals for whole-body movement. The teleoperation process is low-burden and easy to operate, much like piloting. RoboPilot is designed for remote data collection in embodied scenarios. Experimental results demonstrate that RoboPilot significantly enhances data collection efficiency in complex manipulation tasks, achieving a 30% increase compared to methods using 3D mouse and leader-follower systems. It also excels at completing extremely long-horizon tasks in one go. Furthermore, AhaRobot can be used to learn end-to-end policies and autonomously perform complex manipulation tasks, such as pen insertion and cleaning up the floor. We aim to build an affordable yet powerful platform to promote the development of embodied tasks on real devices, advancing more robust and reliable embodied AI. All hardware and software systems are available at https://aha-robot.github.io.

Figures (9)

• Figure 1: Overview of AhaRobot. The system costs only $1,000 for the robot and $1,000 for extra power and computing. Above left: Hardware Configuration of AhaRobot. Above right: Fully Remote Mobile Manipulation Teleoperation RoboPilot. Below: AhaRobot can perform various tasks in daily life.
• Figure 2: Block Diagram of Dual-Joint Control System.
• Figure 3: System Responses with Different Control Strategies.
• Figure 4: RoboPilot Teleoperation Workstation. By capturing the 6D pose of the handle through a web camera, we can fully remotely teleoperate the robot, with the entire setup costing no more than $50. Foot pedals can switch between two modes, respectively controlling the base's movement and the upper limbs' operation.
• Figure 5: Tracking Accuracy of Different Handles.