Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Soft Responsive Materials Enhance Humanoid Safety

Chunzheng Wang, Yiyuan Zhang, Annan Tang, Ziqiu Zeng, Haoran Chen, Quan Gao, Zixuan Zhuang, Boyu Li, Zhilin Xiong, Aoqian Zhang, Ce Hao, Siyuan Luo, Tongyang Zhao, Cecilia Laschi, Fan Shi

Abstract

Humanoid robots are envisioned as general-purpose platforms in human-centered environments, yet their deployment is limited by vulnerability to falls and the risks posed by rigid metal-plastic structures to people and surroundings. We introduce a soft-rigid co-design framework that leverages non-Newtonian fluid-based soft responsive materials to enhance humanoid safety. The material remains compliant during normal interaction but rapidly stiffens under impact, absorbing and dissipating fall-induced forces. Physics-based simulations guide protector placement and thickness and enable learning of active fall policies. Applied to a 42 kg life-size humanoid, the protector markedly reduces peak impact and allows repeated falls without hardware damage, including drops from 3 m and tumbles down long staircases. Across diverse scenarios, the approach improves robot robustness and environmental safety. By uniting responsive materials, structural co-design, and learning-based control, this work advances interact-safe, industry-ready humanoid robots.

Soft Responsive Materials Enhance Humanoid Safety

Abstract

Humanoid robots are envisioned as general-purpose platforms in human-centered environments, yet their deployment is limited by vulnerability to falls and the risks posed by rigid metal-plastic structures to people and surroundings. We introduce a soft-rigid co-design framework that leverages non-Newtonian fluid-based soft responsive materials to enhance humanoid safety. The material remains compliant during normal interaction but rapidly stiffens under impact, absorbing and dissipating fall-induced forces. Physics-based simulations guide protector placement and thickness and enable learning of active fall policies. Applied to a 42 kg life-size humanoid, the protector markedly reduces peak impact and allows repeated falls without hardware damage, including drops from 3 m and tumbles down long staircases. Across diverse scenarios, the approach improves robot robustness and environmental safety. By uniting responsive materials, structural co-design, and learning-based control, this work advances interact-safe, industry-ready humanoid robots.
Paper Structure (35 sections, 3 equations, 10 figures)

This paper contains 35 sections, 3 equations, 10 figures.

Table of Contents

  1. INTRODUCTION
  2. RESULTS
  3. Discussion
  4. MATERIALS AND METHODS
  5. Acknowledgments
  6. Supplementary Movies

Figures (10)

  • Figure 1: Soft responsive material protectors enhance humanoid robot safety. (A) Typical safety hazards associated with humanoid robots during falls and collisions. (B) Soft responsive materials (SRMs) provide effective impact absorption. (C1) Real-time finite-element method (RT-FEM) simulation of impact response. (C2) Protector thickness optimization based on RT-FEM analysis. (C3) Large-scale humanoid impact sampling using physics simulation. (C4) UV-mapping workflow for unfolding 3D robot surfaces into 2D templates for protector design. (C5) Fabrication of surface and joint protectors through monolithic laser cutting. (C6) Full-body humanoid experiments validating the effectiveness of SRM impact protection.
  • Figure 2: SRM mechanical characterization and RT-FEM simulation. (A) Comparison of soft responsive material (SRM) with conventional protective materials, demonstrating its superior impact absorption and mechanical performance. (B) High-frequency impact response profiles of SRM versus common protective materials. (C) Strain-hardening behavior of SRM under increasing compression rate, demonstrating its strain-rate-dependent stiffening. (D) Tensile properties of SRM compared with other protective materials, showing higher stretchability and elastic flexibility. (E1–E2) PMF measurements showing impact distributions with 12 mm and 18 mm SRM pads. (F1–F2) Corresponding RT-FEM results, demonstrating the accuracy of our simulation.
  • Figure 3: Large-scale simulation of common humanoid failure modes and resulting impact analysis. (A) External push-over. (B) Unexpected power loss. (C) Ground-slip fall. (D) Obstacle-induced trip. (E1–E2) Aggregated impact-location statistics across all simulated failure modes, compared with damage patterns from scrapped humanoid robots. (F1–F2) Resulting whole-body force distribution and the corresponding protector placement and thickness determined by co-design. (G) Time-resolved impact-force profiles for major body segments during representative falls. (H) Final protective-pad layout produced by the co-design pipeline.
  • Figure 4: Physical comparison experiments across failure modes with and without protectors. (A1) Power-loss, tripping, and slipping tests conducted without protectors, with yellow triangular markers indicating ground-impact locations. (A2) PMF results after repeated unprotected tests, showing extensive high-pressure regions (red traces) across the robot surface. (B1) Power-loss, tripping, and slipping tests conducted with SRM protectors installed. (B2) PMF results after repeated protected tests, exhibiting minimal high-pressure markings. (C) Violin-plot comparison of impact-intensity distributions with and without protectors. (D) Motor-temperature evaluation of the humanoid robot in protected and unprotected conditions.
  • Figure 5: Protectors reduce the robot’s risk of damaging the environment. (A) Flat-ground push-down tests with and without protectors. PMFs attached to the floor capture the torso–ground impact region. (B) Punching-bag impact tests with and without protectors. PMFs attached to the bag capture the arm–bag impact region. (C) Pressure distributions, high-pressure area fractions, and maximum pressures for the push-down tests. (D) Corresponding statistics for the punching-bag tests. Notably, high-pressure PMFs were used for the push-down tests, while low-pressure PMFs were used for the punching-bag tests.
  • ...and 5 more figures