Reliable navigation in GPS-denied environments remains a critical challenge for autonomous vehicles (AVs), particularly in urban canyons, tunnels, and areas with adverse weather. GPS-based localization systems often fail under these conditions, highlighting the need for resilient, multimodal solutions. This paper introduces a radar-assisted localization approach that combines LiDAR, Inertial Measurement Units (IMUs), and deep learning techniques for robust navigation. The proposed approach combines sensor fusion, Kalman filtering, Gaussian Mixture Models (GMM), and Nonlinear AutoRegressive with eXogenous inputs (NARX) system identification within a unified probabilistic framework. The framework provides continuous real-time localization and environment mapping while enabling short-horizon prediction of the slave robot’s motion based on master robot observations. By forecasting the slave robot’s future states several seconds ahead, the method enhances tracking accuracy, coordination, and overall system robustness in dynamic environments. By fusing sensor data through a Convolutional Recurrent Neural Network (CRNN), our system maintains reliable mapping even in GPS-challenging environments. Radar’s ability to detect objects through weather obstructions, LiDAR’s high-resolution spatial mapping, and IMU data for real-time vehicle tracking work together to reduce the limitations of each individual sensor. To enhance accuracy, we apply Kalman filtering for state estimation and prediction within the GMM-based framework, rather than solely for post-processing or trajectory smoothing, addressing sensor noise and drift. Through simulations and real-world indoor data, we demonstrate the system’s ability to deliver accurate, continuous pose estimation, even in challenging conditions, with low localization errors characterized by RMSE values of 0.12 m, 0.15 m, and 0.28 m along the X, Y, and Z axes, respectively, and sub-meter maximum position deviations. This work represents a significant step toward GPS-independent navigation for AVs and can extend to domains such as aerial drones, offering pathways to more reliable autonomous systems. Future work will address outdoor validation and scalability.

Reliable navigation in GPS-denied environments remains a critical challenge for autonomous vehicles (AVs), particularly in complex indoor and urban settings. GPS-based localization systems often fail under these conditions, highlighting the need for resilient multimodal solutions. In this article, we present a radar-assisted tracking system that integrates LiDAR and inertial measurements within a sensor-fusion architecture to achieve robust navigation. The principal methodological contribution is a unified tracking and prediction framework that combines Bayesian state estimation with learning-based temporal prediction, enabling accurate tracking while continuously forecasting the slave robot’s short-term future state from mapping observations generated by the master robot, with a typical end-to-end perception-to-action latency of 20–60 ms. The communication and prediction forecasting module operates with an update interval below 35 ms, enabling real-time cooperative robotic operation. Sensor data are fused through a pipeline incorporating Gaussian Mixture Models (GMMs) for post-processing, which helps mitigate the limitations associated with individual sensors during edge processing. Moreover, Kalman filtering is employed to mitigate sensor noise and drift, thereby improving state estimation accuracy through trajectory smoothing. The fused spatiotemporal information is subsequently exploited by a Convolutional Recurrent Neural Network (CRNN) coupled with a Nonlinear Autoregressive model with eXogenous Inputs (NARX) to model the robot’s motion dynamics and provide short-horizon state prediction. Through simulations and real-world indoor experiments conducted in GPS-denied environments, we validate the system’s ability to provide accurate and continuous pose estimation with low localization errors. Experimental results show that the proposed framework achieves root-mean-square errors of 0.12 m, 0.15 m, and 0.28 m along the X, Y, and Z axes, respectively, while maintaining sub-meter maximum position deviations throughout the evaluated trajectories. These results confirm that the proposed framework provides reliable localization and predictive state estimation for cooperative robotic navigation in indoor GPS-denied environments. Future work will investigate outdoor validation and extend the framework to additional data-driven decision-making models for future robotic services.