DNN Koopman-Based Deviation Compensation for UGV Path Tracking Control on Coupled Slope and Potholed Road

2026-06-16

AI Summary

This study addresses the degraded path-tracking performance of unmanned ground vehicles in complex off-road environments characterized by coupled slopes and potholes. To this end, the authors propose a deviation compensation approach that integrates deep neural networks with the Koopman operator, combined with a parallel cooperative framework incorporating Laguerre-based model predictive control and event-triggered mechanisms. The method employs an adaptive forgetting recursive least squares algorithm to estimate tire cornering stiffness online, thereby ensuring the feasibility of steering commands while significantly enhancing path-tracking accuracy. Hardware-in-the-loop experiments demonstrate that the proposed strategy improves average tracking performance by more than 11.5% across various challenging driving conditions.

Abstract

Unmanned ground vehicles (UGVs) operating in off-road scenarios are confronted with complex terrain disturbances that can substantially degrade path tracking performance. To address this challenge, this paper proposes a deep neural network (DNN) Koopman-based deviation compensation strategy for UGV path tracking control. Firstly, based on the vehicle dynamic function on coupled slope, an adaptive forgetting recursive least squares method with decoupled error terms is designed to estimate tire cornering stiffness. On this basis, a Laguerre model predictive control (LMPC) path tracking control strategy is designed by incorporating Laguerre functions, which can reduce computational resource usage while maintaining reliable tracking performance across different coupled slope scenarios. Then, by integrating Koopman operator theory with DNN, a DNN Koopman (DK) path deviation compensation method is proposed, which significantly improves the path tracking accuracy of UGV under potholed road disturbances. Furthermore, an event-triggered parallel cooperative (EPC) compensation mechanism that couples LMPC with DK is established based on compensation activation criteria and credibility verification. This mechanism improves path tracking accuracy on potholed road while ensuring the feasibility of overall steering command and stability of vehicle after DK compensation. Finally, a hardware-in-the-loop (HiL) experimental platform is constructed for validation. Experimental results demonstrate that the proposed UGV path tracking strategy improves tracking performance by more than 11.5% across multiple operating conditions.

Problem

• UGV path tracking
• terrain disturbances
• coupled slope
• potholed road
• tracking performance degradation

Innovation

• Koopman operator
• deep neural network
• model predictive control
• path tracking
• deviation compensation