Exploring the dynamic properties and motion reproducibility of a small upper-body humanoid robot with 13-DOF pneumatic actuation for data-driven control

2026-03-15

AI Summary

This study addresses the challenge of precise trajectory tracking in high-degree-of-freedom pneumatic humanoid robots, which is hindered by actuator nonlinearities and time delays. The authors develop a compact 13-degree-of-freedom upper-body pneumatic humanoid platform and demonstrate, for the first time in such highly articulated systems, the high repeatability of motion execution. Focusing on a 4-degree-of-freedom arm subsystem, they propose a multilayer perceptron (MLP)-based data-driven controller that explicitly compensates for system time delays. Trained on randomized motion data, the network directly generates pressure commands to track arbitrary trajectories. Experimental results show that this approach significantly outperforms conventional PID control in trajectory tracking accuracy, thereby validating the efficacy and superiority of data-driven strategies for controlling complex pneumatic robotic systems.

Technology Category

Intelligent Robots: Behavior Learning & ControlHumans and AI: Human-Aware Planning and Behavior PredictionMachine Learning: Learning with Manifolds

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyEconomics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Pneumatically-actuated anthropomorphic robots with high degrees of freedom (DOF) offer significant potential for physical human-robot interaction. However, precise control of pneumatic actuators is challenging due to their inherent nonlinearities. This paper presents the development of a compact 13-DOF upper-body humanoid robot. To assess the feasibility of an effective controller, we first investigate its key dynamic properties, such as actuation time delays, and confirm that the system exhibits highly reproducible behavior. Leveraging this reproducibility, we implement a preliminary data-driven controller for a 4-DOF arm subsystem based on a multilayer perceptron with explicit time delay compensation. The network was trained on random movement data to generate pressure commands for tracking arbitrary trajectories. Comparative evaluations with a traditional PID controller demonstrate superior trajectory tracking performance, highlighting the potential of data-driven approaches for controlling complex, high-DOF pneumatic robots.

Problem

• pneumatic actuation
• high-DOF humanoid robot
• nonlinear control
• trajectory tracking
• dynamic reproducibility

Innovation

• pneumatic actuation
• data-driven control
• motion reproducibility
• time delay compensation
• humanoid robot