Humanoids gain extra robotic arms for better multitasking and balance
Humanoid SRL: Augmenting Humanoids with Supernumerary Limbs for Coordinated Loco-Manipulation
Robotics
Summary
Humanoid robots traditionally have two arms, which limits what they can do when both arms are busy or when extra support is needed. The authors added a third robotic arm to a humanoid robot to see how it improves its ability to move and manipulate objects at the same time. They used advanced computer planning and learning methods to control the robot's whole body and the extra arm together. Their tests show that the robot can perform new and more complex actions, including tasks guided by vision, without losing balance. This suggests robots can be designed with additional limbs to expand their capabilities beyond human-like forms.
What this means in practice
- •For robotics engineers: Design and control of humanoid robots enhanced with extra arms to perform complex manipulation and support tasks simultaneously.
- •For industrial automation teams: Implement robots capable of multi-arm coordination for handling objects and maintaining balance in dynamic work environments.
Authors
Fukang Liu, Feiyang Wu, Paul Barsa, Jaehwi Jang, Akshat Jain, Zhigen Zhao, Yipu Chen, Zhaoyuan Gu, Nikhil Vemuri, Anshul Chandaliya, Kaijie Zhu, Sean Lublinsky, Matthew Zhu, Tony G. Chen, Ye Zhao
Abstract
Humanoid robots are envisioned to perform diverse human-level tasks through their anthropomorphic morphology. Their dual-arm configuration enables a broad range of everyday actions. Yet, as in humans, this morphology can constrain loco-manipulation when both arms are occupied or additional contacts are required beyond their reach. Supernumerary robotic limbs (SRLs) offer a way to extend these capabilities, but their integration requires the added limb to be coordinated with whole-body motion and balance. In this study, we develop and integrate a supernumerary arm into a humanoid platform to investigate how morphological augmentation reshapes its feasible action space. Through quantitative analysis and hardware experiments across two configurations, we show how the additional limb expands whole-body interaction capabilities by enabling manipulation and support to be coordinated beyond the constraints of the native dual-arm configuration. To control this augmented morphology, we leverage model-based trajectory optimization (TO) to generate dynamically feasible motions for goal-conditioned reinforcement learning (RL) controllers. The controllers are trained in simulation and transferred to hardware in a zero-shot manner, enabling coordinated whole-body skills for contact-rich tri-arm loco-manipulation. We further show vision-guided autonomous execution on selected tasks using diffusion policies trained from hardware demonstrations. Our findings suggest that humanoid morphology need not be restricted to human-like forms, but can be reimagined as an extensible design space for robotic augmentation.