Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Refined Motion Compensation with Soft Laser Manipulators using Data-Driven Surrogate Models

Yongjun Yan, Qingpeng Ding, Mingwu Li, Junyan Yan, Shing Shin Cheng

TL;DR

The paper addresses motion compensation for a soft, cable-driven laser manipulator used in non-contact liver tumor ablation under rhythmic organ motion. It proposes a data-driven surrogate model built from Spectral Submanifolds learned from vibration data and embedded into a Model Predictive Control framework, solved via an SQP-based solver. The SSM-MPC achieves a mean tracking error of $0.27$ mm, outperforming Linear Koopman ($0.36$ mm) and Constant-Curvature ($0.58$ mm) baselines, and demonstrates design-agnostic compatibility across different soft manipulators. This approach enables accurate, real-time motion compensation with interchangeable hardware, potentially improving safety and precision in robot-assisted laser ablation therapies.

Abstract

Non-contact laser ablation, a precise thermal technique, simultaneously cuts and coagulates tissue without the insertion errors associated with rigid needles. Human organ motions, such as those in the liver, exhibit rhythmic components influenced by respiratory and cardiac cycles, making effective laser energy delivery to target lesions while compensating for tumor motion crucial. This research introduces a data-driven method to derive surrogate models of a soft manipulator. These low-dimensional models offer computational efficiency when integrated into the Model Predictive Control (MPC) framework, while still capturing the manipulator's dynamics with and without control input. Spectral Submanifolds (SSM) theory models the manipulator's autonomous dynamics, acknowledging its tendency to reach equilibrium when external forces are removed. Preliminary results show that the MPC controller using the surrogate model outperforms two other models within the same MPC framework. The data-driven MPC controller also supports a design-agnostic feature, allowing the interchangeability of different soft manipulators within the laser ablation surgery robot system.

Refined Motion Compensation with Soft Laser Manipulators using Data-Driven Surrogate Models

TL;DR

The paper addresses motion compensation for a soft, cable-driven laser manipulator used in non-contact liver tumor ablation under rhythmic organ motion. It proposes a data-driven surrogate model built from Spectral Submanifolds learned from vibration data and embedded into a Model Predictive Control framework, solved via an SQP-based solver. The SSM-MPC achieves a mean tracking error of mm, outperforming Linear Koopman ( mm) and Constant-Curvature ( mm) baselines, and demonstrates design-agnostic compatibility across different soft manipulators. This approach enables accurate, real-time motion compensation with interchangeable hardware, potentially improving safety and precision in robot-assisted laser ablation therapies.

Abstract

Non-contact laser ablation, a precise thermal technique, simultaneously cuts and coagulates tissue without the insertion errors associated with rigid needles. Human organ motions, such as those in the liver, exhibit rhythmic components influenced by respiratory and cardiac cycles, making effective laser energy delivery to target lesions while compensating for tumor motion crucial. This research introduces a data-driven method to derive surrogate models of a soft manipulator. These low-dimensional models offer computational efficiency when integrated into the Model Predictive Control (MPC) framework, while still capturing the manipulator's dynamics with and without control input. Spectral Submanifolds (SSM) theory models the manipulator's autonomous dynamics, acknowledging its tendency to reach equilibrium when external forces are removed. Preliminary results show that the MPC controller using the surrogate model outperforms two other models within the same MPC framework. The data-driven MPC controller also supports a design-agnostic feature, allowing the interchangeability of different soft manipulators within the laser ablation surgery robot system.
Paper Structure (7 sections, 5 equations, 4 figures)

This paper contains 7 sections, 5 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Mechanisms of Soft Laser Manipulator
  3. Controller Implementation Pipeline
  4. Experimental Evaluation
  5. Control Performance Comparison with Other Models
  6. Design Agnostic Feature Evaluation
  7. Conclusion

Figures (4)

  • Figure 1: Schematic diagram of a soft laser manipulator in minimally invasive liver tumor ablation surgery. (a) Demonstration of the motion compensation mechanism with the surrogate models of the soft laser manipulator. (b) Clinical setup of the minimally invasive tumor ablation surgery with soft laser manipulator. (c) CAD models of the soft laser manipulator robotics system. (d) Exposed electro-mechanical subunits of one of the cable actuation systems. The four cable actuation systems are mounted in pairwise opposition in the cable actuation modules.
  • Figure 2: Experimental platform for the soft laser manipulator.
  • Figure 3: Reference tracking performance comparison of the SSM-MPC (row 1, column 1, red), LK-MPC (row 1, column 2, blue), and CC-MPC (row 1, column 3, yellow). Open-loop prediction accuracy comparison using identical initial states and control sequences (row 2).
  • Figure 4: Design-agnostic feature evaluation of the SSM-MPC controller. (a) Soft manipulator with a rectangular curve and 70 Shore A hardness white polyurethane elastomer. (b) Learned submanifolds for the manipulator in (a). (c) Tracking performance of the SSM-MPC controller with the manipulator in (a). (d) Soft manipulator with a diamond curve and 90 Shore A hardness black polyurethane elastomer. (e) Learned submanifolds for the manipulator in (d). (f) Tracking performance of the SSM-MPC controller with the manipulator in (d).