15/01/2025
📢 New Paper Published in World Electric Vehicle Journal! 🚜
Check out this important research:
"A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial" by Yangming Hu, Liyou Xu, Xianghai Yan, Ningjie Chang, Qigang Wan, and Yiwei Wu.
🔎This paper addresses the challenges posed by GPS denial in agricultural environments, such as those influenced by forest cover or adverse weather conditions, where traditional GNSS/INS integrated navigation systems are disrupted by unstable satellite signals. This instability results in the divergence of navigation errors, compromising the accuracy and stability of autonomous tractor navigation.
⚡To enhance positioning precision, the paper proposes a model that combines Convolutional Neural Networks (CNN) with Bidirectional Long Short-Term Memory Networks (BiLSTM) to assist integrated navigation. The CNN-BiLSTM model is trained when GNSS signals are available, and in the event of signal loss, the model predicts navigation data, ensuring reliable, continuous, and stable positioning.
💡The model's effectiveness and reliability are validated using real-world data from a tractor simulating fieldwork. Experimental results demonstrate that whether GPS fails for an extended or brief period, the model exhibits a fitting accuracy comparable to real GPS, proving the feasibility of replacing GPS with the neural network model under GPS denial conditions.
🔗 Read the full paper here: https://brnw.ch/21wQ14P
This article is part of the Special Issue on Advancements in Autonomous Vehicles: Security, Optimization, and Future Challenges. ⚙️
In farmland environments where GNSS signals are obstructed, such as forested areas or in adverse weather conditions, traditional GNSS/INS integrated navigation systems suffer from positioning errors and instability. To address this, a model-assisted integrated navigation system is proposed, combinin...
