NMPC-Augmented Visual Navigation and Safe Learning Control for Large-Scale Mobile Robots

2026-01-02

arXiv.org

AI Summary

This work addresses the challenges of pose drift and control instability in large-scale mobile robots operating on loose, slippery terrain due to insufficient traction. To this end, a four-module cooperative framework is proposed, integrating stereo-vision-based pose estimation, high-order nonlinear model predictive control (NMPC), a deep neural network-based low-level controller, and a logarithmic barrier-based safety monitoring mechanism. The approach uniquely combines high-order NMPC with a learning-based low-level controller and introduces a logarithmic safety barrier, achieving system-wide safety and exponential stability of actuators through synchronized multi-rate heterogeneous module coordination. Experimental validation on a 6,000-kg dual electro-hydrostatic actuation platform demonstrates that the method enables low-latency, high-precision pose tracking and full-stack safety guarantees under severe slippage conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

A large-scale mobile robot (LSMR) is a high-order multibody system that often operates on loose, unconsolidated terrain, which reduces traction. This paper presents a comprehensive navigation and control framework for an LSMR that ensures stability and safety-defined performance, delivering robust operation on slip-prone terrain by jointly leveraging high-performance techniques. The proposed architecture comprises four main modules: (1) a visual pose-estimation module that fuses onboard sensors and stereo cameras to provide an accurate, low-latency robot pose, (2) a high-level nonlinear model predictive control that updates the wheel motion commands to correct robot drift from the robot reference pose on slip-prone terrain, (3) a low-level deep neural network control policy that approximates the complex behavior of the wheel-driven actuation mechanism in LSMRs, augmented with robust adaptive control to handle out-of-distribution disturbances, ensuring that the wheels accurately track the updated commands issued by high-level control module, and (4) a logarithmic safety module to monitor the entire robot stack and guarantees safe operation. The proposed low-level control framework guarantees uniform exponential stability of the actuation subsystem, while the safety module ensures the whole system-level safety during operation. Comparative experiments on a 6,000 kg LSMR actuated by two complex electro-hydrostatic drives, while synchronizing modules operating at different frequencies.

Problem

• large-scale mobile robot
• slip-prone terrain
• navigation stability
• safety assurance
• traction loss

Innovation

• Nonlinear Model Predictive Control (NMPC)
• Visual Navigation
• Safe Learning Control
• Deep Neural Network Control
• Large-Scale Mobile Robots