Scholarlink

<p>The navigation of an autonomous vehicle depends mostly on the integration of multi-sensor data from sources such as LiDAR, GPS, radar, and cameras. Issues like sensor noise, data asynchrony, and fusion inaccuracies hamper reliable real-time decision-making. This paper proposes an optimized multi-sensor data fusion framework integrating big data analytics with modern filtering techniques to increase navigation accuracy and system robustness. The proposed model integrates Kalman Filter (KF), Extended Kalman Filter (EKF), and Adaptive Neuro-Fuzzy Inference System (ANFIS) for dynamic state estimation and adaptive noise accommodation. In addition, sensor reliability and position tracking are enhanced via Bayesian data fusion and Particle Filter. Simulation results show that the proposed technique is evidently superior to existing models in accuracy (1.5 RMSE), convergence time (0.98&#xa0;s), and latency (50 ms). The fusion system enhances stability and responsiveness in autonomous navigation and offers an intelligent transportation framework that can be deployed efficiently at a real-time scale.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ANFIS-Based Multi-Sensor Data Fusion Model for Optimized Autonomous Vehicle Navigation Using Big Data and Filtering Techniques

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • Sanjay Kumar,
  • Anand Ranjan,
  • Surabhi Saxena,
  • Ashish

摘要

The navigation of an autonomous vehicle depends mostly on the integration of multi-sensor data from sources such as LiDAR, GPS, radar, and cameras. Issues like sensor noise, data asynchrony, and fusion inaccuracies hamper reliable real-time decision-making. This paper proposes an optimized multi-sensor data fusion framework integrating big data analytics with modern filtering techniques to increase navigation accuracy and system robustness. The proposed model integrates Kalman Filter (KF), Extended Kalman Filter (EKF), and Adaptive Neuro-Fuzzy Inference System (ANFIS) for dynamic state estimation and adaptive noise accommodation. In addition, sensor reliability and position tracking are enhanced via Bayesian data fusion and Particle Filter. Simulation results show that the proposed technique is evidently superior to existing models in accuracy (1.5 RMSE), convergence time (0.98 s), and latency (50 ms). The fusion system enhances stability and responsiveness in autonomous navigation and offers an intelligent transportation framework that can be deployed efficiently at a real-time scale.