ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2502.16908
36
0

Design of a low-cost and lightweight 6 DoF bimanual arm for dynamic and contact-rich manipulation

24 February 2025
Jaehyung Kim
Jiho Kim
Dongryung Lee
Yujin Jang
Beomjoon Kim
ArXivPDFHTML
Abstract

Dynamic and contact-rich object manipulation, such as striking, snatching, or hammering, remains challenging for robotic systems due to hardware limitations. Most existing robots are constrained by high-inertia design, limited compliance, and reliance on expensive torque sensors. To address this, we introduce ARMADA (Affordable Robot for Manipulation and Dynamic Actions), a 6 degrees-of-freedom bimanual robot designed for dynamic manipulation research. ARMADA combines low-inertia, back-drivable actuators with a lightweight design, using readily available components and 3D-printed links for ease of assembly in research labs. The entire system, including both arms, is built for just 6,100.Eacharmachievesspeedsupto6.16m/s,almosttwicethatofmostcollaborativerobots,withacomparablepayloadof2.5kg.WedemonstrateARMADAcanperformdynamicmanipulationlikesnatching,hammering,andbimanualthrowinginreal−worldenvironments.Wealsoshowcaseitseffectivenessinreinforcementlearning(RL)bytraininganon−prehensilemanipulationpolicyinsimulationandtransferringitzero−shottotherealworld,aswellashumanmotionshadowingfordynamicbimanualobjectthrowing.ARMADAisfullyopen−sourcedwithdetailedassemblyinstructions,CADmodels,URDFs,simulation,andlearningcodes.WehighlyrecommendviewingthesupplementaryvideoatthishttpsURL.6,100. Each arm achieves speeds up to 6.16m/s, almost twice that of most collaborative robots, with a comparable payload of 2.5kg. We demonstrate ARMADA can perform dynamic manipulation like snatching, hammering, and bimanual throwing in real-world environments. We also showcase its effectiveness in reinforcement learning (RL) by training a non-prehensile manipulation policy in simulation and transferring it zero-shot to the real world, as well as human motion shadowing for dynamic bimanual object throwing. ARMADA is fully open-sourced with detailed assembly instructions, CAD models, URDFs, simulation, and learning codes. We highly recommend viewing the supplementary video atthis https URL.6,100.Eacharmachievesspeedsupto6.16m/s,almosttwicethatofmostcollaborativerobots,withacomparablepayloadof2.5kg.WedemonstrateARMADAcanperformdynamicmanipulationlikesnatching,hammering,andbimanualthrowinginreal−worldenvironments.Wealsoshowcaseitseffectivenessinreinforcementlearning(RL)bytraininganon−prehensilemanipulationpolicyinsimulationandtransferringitzero−shottotherealworld,aswellashumanmotionshadowingfordynamicbimanualobjectthrowing.ARMADAisfullyopen−sourcedwithdetailedassemblyinstructions,CADmodels,URDFs,simulation,andlearningcodes.WehighlyrecommendviewingthesupplementaryvideoatthishttpsURL.

View on arXiv
@article{kim2025_2502.16908,
  title={ Design of a low-cost and lightweight 6 DoF bimanual arm for dynamic and contact-rich manipulation },
  author={ Jaehyung Kim and Jiho Kim and Dongryung Lee and Yujin Jang and Beomjoon Kim },
  journal={arXiv preprint arXiv:2502.16908},
  year={ 2025 }
}
Comments on this paper