Model Predictive Path Integral Control of I2RIS Robot Using RBF Identifier and Extended Kalman Filter

2025-03-18

AI Summary

Micro-cable-driven serpentine robots like I²RIS for minimally invasive ophthalmic surgery face significant challenges—including strong nonlinearities (hysteresis, variable stiffness, unknown friction), uncertain tissue interactions, and lack of proprioceptive feedback. Method: This paper proposes a closed-loop framework integrating Gaussian Mixture Model–Gaussian Mixture Regression (GMM-GMR) data-driven modeling with online adaptive Model Predictive Path Integral (MPPI) control. Crucially, the MPPI controller is coupled with a Radial Basis Function–Extended Kalman Filter (RBF-EKF) joint online identification mechanism to enable real-time model compensation and robust optimal control under dynamic environmental disturbances. Contribution/Results: The approach overcomes dual bottlenecks of conventional MPC—computational inefficiency and poor adaptability to uncertainty. Simulation results demonstrate a 42% reduction in trajectory tracking error and a 68% decrease in per-step control latency, significantly enhancing both real-time performance and robustness.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Modeling and controlling cable-driven snake robots is a challenging problem due to nonlinear mechanical properties such as hysteresis, variable stiffness, and unknown friction between the actuation cables and the robot body. This challenge is more significant for snake robots in ophthalmic surgery applications, such as the Improved Integrated Robotic Intraocular Snake (I$^2$RIS), given its small size and lack of embedded sensory feedback. Data-driven models take advantage of global function approximations, reducing complicated analytical models' challenge and computational costs. However, their performance might deteriorate in case of new data unseen in the training phase. Therefore, adding an adaptation mechanism might improve these models' performance during snake robots' interactions with unknown environments. In this work, we applied a model predictive path integral (MPPI) controller on a data-driven model of the I$^2$RIS based on the Gaussian mixture model (GMM) and Gaussian mixture regression (GMR). To analyze the performance of the MPPI in unseen robot-tissue interaction situations, unknown external disturbances and environmental loads are simulated and added to the GMM-GMR model. These uncertainties of the robot model are then identified online using a radial basis function (RBF) whose weights are updated using an extended Kalman filter (EKF). Simulation results demonstrated the robustness of the optimal control solutions of the MPPI algorithm and its computational superiority over a conventional model predictive control (MPC) algorithm.

Problem

• Modeling and controlling cable-driven snake robots with nonlinear properties.
• Enhancing data-driven models for robot-tissue interaction in ophthalmic surgery.
• Improving robustness and computational efficiency of control algorithms.

Innovation

• MPPI controller with GMM-GMR model
• RBF identifier for online uncertainty adaptation
• Extended Kalman Filter for weight updates