Learning-based Delay Compensation for Enhanced Control of Assistive Soft Robots

2025-04-16

AI Summary

To address degraded trajectory tracking accuracy in medical assistive soft robots caused by inherent input delays (on the millisecond scale), this paper proposes a model-free, adaptive online delay compensation method. The approach innovatively integrates a Kernel Recursive Least Squares Tracker (KRLST) with a Legendre Delay Network (LDN) to construct a lightweight dynamic delay prediction module, embedded within a Smith Predictor–inspired approximate feedback architecture for closed-loop compensation. The method requires no prior system modeling, incurs low computational overhead (<5 ms), and ensures strong real-time performance suitable for embedded deployment. Experimental validation on a two-module soft robotic arm demonstrates statistically significant improvement in trajectory tracking accuracy (p < 0.01). This work establishes a robust, delay-resilient control paradigm for time-critical clinical assistance tasks.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Hardware-aware ML
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Soft robots are increasingly used in healthcare, especially for assistive care, due to their inherent safety and adaptability. Controlling soft robots is challenging due to their nonlinear dynamics and the presence of time delays, especially in applications like a soft robotic arm for patient care. This paper presents a learning-based approach to approximate the nonlinear state predictor (Smith Predictor), aiming to improve tracking performance in a two-module soft robot arm with a short inherent input delay. The method uses Kernel Recursive Least Squares Tracker (KRLST) for online learning of the system dynamics and a Legendre Delay Network (LDN) to compress past input history for efficient delay compensation. Experimental results demonstrate significant improvement in tracking performance compared to a baseline model-based non-linear controller. Statistical analysis confirms the significance of the improvements. The method is computationally efficient and adaptable online, making it suitable for real-world scenarios and highlighting its potential for enabling safer and more accurate control of soft robots in assistive care applications.

Problem

• Compensate time delays in soft robot control
• Improve tracking performance in assistive soft robots
• Enhance safety and accuracy in healthcare applications

Innovation

• Learning-based nonlinear state predictor approximation
• KRLST for online system dynamics learning
• LDN for efficient delay compensation