Machine Learning-Based Self-Localization Using Internal Sensors for Automating Bulldozers

2025-06-08

AI Summary

To address autonomous bulldozer localization failure in RTK-GNSS-denied environments—common in mining operations—this paper proposes a satellite-independent, multi-sensor fusion localization method. First, we construct the first bulldozer-specific odometry dataset, incorporating operation-critical sensors such as blade pose and hydraulic pressure. Second, we employ LSTM/MLP models to fuse IMU, wheel-speed, and hydraulic measurements for robust local velocity estimation. Finally, an Extended Kalman Filter (EKF) recursively integrates these estimates to compute global pose. The method significantly enhances robustness under challenging conditions—including wheel slip, steep inclines, and excavation—where conventional kinematic models degrade rapidly. In serpentine driving and other representative scenarios, positional drift is reduced by 42% compared to traditional approaches. Experimental validation confirms both the feasibility and superiority of this GNSS-free solution for real-world mining applications.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Self-localization is an important technology for automating bulldozers. Conventional bulldozer self-localization systems rely on RTK-GNSS (Real Time Kinematic-Global Navigation Satellite Systems). However, RTK-GNSS signals are sometimes lost in certain mining conditions. Therefore, self-localization methods that do not depend on RTK-GNSS are required. In this paper, we propose a machine learning-based self-localization method for bulldozers. The proposed method consists of two steps: estimating local velocities using a machine learning model from internal sensors, and incorporating these estimates into an Extended Kalman Filter (EKF) for global localization. We also created a novel dataset for bulldozer odometry and conducted experiments across various driving scenarios, including slalom, excavation, and driving on slopes. The result demonstrated that the proposed self-localization method suppressed the accumulation of position errors compared to kinematics-based methods, especially when slip occurred. Furthermore, this study showed that bulldozer-specific sensors, such as blade position sensors and hydraulic pressure sensors, contributed to improving self-localization accuracy.

Problem

• Develop RTK-GNSS-independent self-localization for bulldozers
• Estimate velocities via ML and EKF for global positioning
• Reduce position errors in slip-prone mining conditions

Innovation

• Machine learning model estimates local velocities
• Extended Kalman Filter integrates velocity estimates
• Bulldozer-specific sensors enhance localization accuracy