HoLoArm: Deformable Arms for Collision-Tolerant Quadrotor Flight
NGOC QUANG PHAM, Jonas Eschmann, Yang Zhou, Alejandro Ojeda Olarte, Giuseppe Loianno, Van Ho
AI summary
Problem
Rigid drone frames are vulnerable to collisions in dynamic environments, while existing soft-drone designs lack effective axial impact tolerance, scalability, and reliable post-impact control.
Approach
HoLoArm features TPU-based, nodus-inspired joints that passively deform to absorb impacts, combined with a reinforcement learning policy that stabilizes flight and accelerates recovery without requiring precise dynamic models.
Key results
- Nodus-inspired compliant joints enable multi-directional passive deformation
- Post-impact recovery achieved within 0.3–0.6 seconds depending on impact direction
- Survives collisions up to 7.6 m/s while maintaining stable flight with a 540 g payload
- Reinforcement learning control successfully compensates for nonlinear soft-rigid dynamics
Why it matters
Provides a scalable, mechanically simple pathway for deploying resilient drones in human-shared and cluttered spaces.
Abstract
The increasing use of drones in human-centric appli- cations highlights the need for designs that can survive collisions and recover rapidly, minimizing risks to both humans and the environment. We present HoLoArm, a quadrotor with compliant arms inspired by the nodus structure of dragonfly wings. This design provides natural flexibility and resilience while preserv- ing flight stability, which is further reinforced by the integration of a Reinforcement Learning (RL) control policy that enhances both recovery and hovering performance. Experimental results demonstrate that HoLoArm can passively deform in any direction, including axial one, and recover within 0.3–0.6 s depending on the direction and level of the impact. The drone can survive collisions at speeds up to 7.6 m/s and carry a 540 g payload while maintaining stable flight. This work contributes to the morphological design of soft aerial robots with high agility and reliable safety, enabling operation in cluttered and human shared environments, and lays thegroundworkforfuturefullysoftdronesthatintegratecompliant structures with intelligent control.