Research Analyzer
← Back ICRA 2026

Enhancing Dual-Loop Pressure Control in Pneumatic Soft Robotics with a Comparison of Evolutionary Algorithms for PID & FOPID Controller Tuning

Jacqueline Libby, Mostafa Mo. Massoud, Paulo Henrique Teixeira Franca Alves

PDF

AI summary

Key figure (auto-extracted from paper)
A dual-loop pneumatic control architecture combined with evolutionary algorithm-tuned FOPID and PID controllers significantly reduces pressure oscillations and optimizes dynamic response for affordable soft robots.
Pneumatic control Soft robotics FOPID tuning Evolutionary optimization Dual-loop control Pressure regulation

Problem

Affordable on/off valves in pneumatic soft robots introduce nonlinear flow discontinuities and pressure oscillations that manual PID tuning cannot adequately address.

Approach

The authors implement a dual-loop control system for the pump and valve, then use genetic algorithm, particle swarm optimization, and simulated annealing to automatically tune PID and FOPID parameters, validating results through Simscape simulations and real-world experiments.

Key results

  • Dual-loop control reduces pressure fluctuations by 68.28% compared to single-loop schemes
  • FOPID tuned with PSO and GA yields superior rise and peak time performance
  • PID tuned with GA and PSO better minimizes overshoot
  • Optimized controllers enable stable manipulation of delicate loads like water-filled cups

Why it matters

Provides a practical, validated tuning framework that helps engineers maximize control performance while using cost-effective pneumatic hardware.

Abstract

The control of pneumatic soft robotics is challenging due to nonlinearites arising from many factors including pneu- matic system components and material properties of the soft actuator. Manual methods for PID controller tuning are inade- quate for the nonlinear and time-variant dynamics present in soft robotics. Affordable pneumatic components such as on/off valves cause discontinuities in flow rate, introducing nonlinearities and oscillatory fluctuations into the system. This study proposes a dual-loop control system: one for PID and Fractional-Order PID (FOPID) control of a solenoid valve that feeds air into the actuator, and another for PID control of the pump upstream of the valve. The PID and FOPD parameters are optimized using evolutionary algorithms: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA). Simulations and real-world experiments are conducted to validate the optimized parameters. Our results demonstrate that the dual- loop hardware configuration reduces fluctuations from the valves compared with a single-loop control scheme. The experimental statistical analysis confirms that FOPID achieves the highest significant improvements in rise time (PSO) and peak time (GA, PSO), while PID performs better for overshoot (GA, PSO). These findings highlight the importance of selecting an appropriate optimization algorithm based on the specific control objective, as FOPID does not outperform PID in every metric across all methods.

Index terms

Hydraulic/Pneumatic Actuators Modeling Control and Learning for Soft Robots Hardware-Software Integration in Robotics

Related papers