Research Analyzer
← Back ICRA 2026

L-BIRD: Lightweight Bio-Inspired Rotary-Wing Drone

Xuwen Guo, Mingxuan Zhu, Yinghong Tian

PDF

AI summary

Key figure (auto-extracted from paper)
L-BIRD achieves accurate, real-time biomimetic attitude control and adaptive landing on complex surfaces using a lightweight MPC framework optimized for resource-constrained hardware.
bio-inspired drones model predictive control primal-dual neural network lightweight robotics adaptive landing embedded control

Problem

Current biomimetic drones lack flexible attitude control and adaptive landing capabilities on complex surfaces, while traditional model predictive control is too computationally heavy for real-time deployment on lightweight, low-power hardware.

Approach

The authors designed a spherical-shell drone that mimics bird posture and landing, paired with a bio-inspired MPC controller optimized via sparse matrices and multi-path primal-dual neural networks to run efficiently on embedded systems.

Key results

  • Spherical-shell design enabling adaptive landing and immediate re-takeoff on complex surfaces
  • Bio-inspired parameter pairs generating realistic bird-like attitude trajectories across flight phases
  • Sparse matrix and multi-path PDNN optimization reducing RAM usage by 39.3%
  • Attitude tracking mean-square error reduced to 0.0042 rad in simulations and real-world tests

Why it matters

Advances lightweight, agile UAV design for complex terrain navigation and real-time embedded biomimetic control.

Abstract

In nature, birds exhibit outstanding attitude control, enabling flexible and efficient takeoff, hovering and landing — capabilities that have not been fully replicated. Thus, we introduce the lightweight bio-inspired rotary-wing drone (L- BIRD). It incorporates a spherical structure, which can imitate birds’ attitude variation and land on complex surfaces adaptively. L-BIRD employs a model predictive control (MPC) framework to enable real-time tracking of bird-like attitude trajectories derived from bio-inspired parameter pairs. To facilitate lightweight deployment on resource-constrained hardware platforms, we improve MPC framework by multi-path primal-dual neural network (PDNN), matrix sparsity and multiplicative optimiza- tion. Experimental results, both in simulations and real-world deployments, demonstrate that L-BIRD realizes accurate and efficient biomimetic attitude control and diverse environmental adaptability. The attitude trajectory mean-square error (MSE) decreases to 0.0042 rad, random access memory (RAM) usage reduces by 39.3%.

Index terms

Biologically-Inspired Robots Aerial Systems: Mechanics and Control Embedded Systems for Robotic and Automation

Related papers