It was seen that the global pose of the robot accumulates error and suffers from drift over time but can be improved with an optimization implementation comparing position points to a generated submap which is planned as a future research direction.
Abstract
This research entails the development of a deep learning-based framework to localize a steerable mobile robot using the following sensors: two-dimensional laser scanner, inertial measurement unit (IMU) and wheel encoders. Current methods for sensor fusion such as the Extended Kalman Filter (EKF) which rely heavily on linear approximations and sensor input quality are sensitive to large angular rotations and accelerations resulting in increased error. The results of this work will provide an accurate deep learning framework for precise nonlinear positioning. The localization problem is structured as a time series pose regression problem. Estimates for pose are provided using two successive laser scans and a designed Recurrent Convolutional Neural Network (RCNN) to fuse the remaining sensors which receive measurement data at varying rates. This framework is composed of one convolutional network block for the laser scanning data alongside several recurrent network blocks to accommodate the remaining sensors. Furthermore, the robot’s selected trajectory is decomposed into sequences for computational efficiency during investigation. The framework is first developed in simulation using MATLAB with PyTorch and then a physical experiment is performed using a front wheel steering, rear wheel drive robot, known as the Patrolbot outfitted with two LIDARs, wheel encoders and IMU with positioning results compared to the ground truth. It was seen that the global pose of the robot accumulates error and suffers from drift over time but can be improved with an optimization implementation comparing position points to a generated submap which is planned as a future research direction. This research has various applications and can be used to localize robots in a laboratory setting with moving obstacles (environment obstacle position varies) or for the robot to successfully park itself at a goal point with high accuracy. In addition, there minimal research investigations in the area of deep learning sensor fusion with virtually no investigations performed prior to 2021.
Reliable localization is required for autonomous mobile robots when individual sensing streams become noisy, intermittent, or unavailable. This study evaluates a multi-sensor fusion framework that combines LiDAR, monocular vision, GPS, UWB, and IMU data using three strategies: (i) a baseline Extended Kalman Filter (EKF); (ii) a dual-stage sequential EKF that refines LiDAR-Inertial Odometry (LIO) before the final fusion stage; and (iii) a hybrid learning-filtering approach in which modality-specific learned motion and position estimates are incorporated into an EKF. All evaluations were conducted in ROS-Gazebo under nominal operation and controlled sensor-degradation/dropout conditions. Relative to the controller-derived reference trajectory, the standard EKF achieved 0.2235 m RMSE and the dual-stage EKF achieved 0.2029 m RMSE, a descriptive reduction of approximately 9.2% for the reported run. The hybrid learning-EKF achieved 0.212 m RMSE under nominal sensing and 0.384 m RMSE during the tested failure sequence. These results support the evaluated fusion designs under the reported simulation conditions, but they do not establish statistical generalization or universal real-world resilience; independent ground truth, repeated trials, GPS ablation, and physical validation remain necessary.
Muhammad Shahzad Alam Khan, Anas Bin Aqeel, Hassan Elahi et al.· Scientific Reports· 0 citations
Localization is a fundamental requirement for autonomous mobile robot navigation. Several localization techniques exist, but they often require extensive installation of beacons, careful parameter tuning, high computational requirements, or an immense amount of training data. Environmental (e.g., indoor)/resource constraints, sensor degradation, and sudden pose discontinuities can make such methods unreliable. This creates a critical gap: the lack of a simple, lightweight localization method that can operate as a primary localization method or in parallel with other classical systems and provide reliable pose estimates during primary localization system failures. Thus, this paper proposes a lightweight, deep learning (DL)-based, two-dimensional LiDAR localization method. The approach combines LiDAR scan range data with eleven proposed handcrafted geometric features to train a Convolutional Multi-Layer Perceptron (ConvMLP) regression model for predicting the two-dimensional location of a robot, which is further smoothed by an augmented recursive Extended Kalman filter (EKF). The overall system is validated in three real-world environments. The results are compared against various existing machine learning (ML) models and other well-known localization techniques. The experimental results demonstrate a 280 Hz pose-update rate, achieving a 13 cm Root Mean Square Error (RMSE) using the ConvMLP model alone, which further reduces to 5 cm when fused with the recursive EKF.
Harsha Keladi Ganapathi, S. Mukhopadhyay· Applied Sciences· 0 citations
Autonomous robot localization is a critical function that enables intelligent navigation, motion planning, and interaction within structured and unstructured environments. Before 2019, significant advancements were made by integrating multiple sensors such as wheel encoders, IMUs, LiDAR, cameras, ultrasonic sensors, and GNSS. Since each sensor has limitations like drift, uncertainty, and environmental sensitivity, advanced sensor fusion techniques were developed to improve localization accuracy and reliability. This study examines localization methods based on probabilistic filtering approaches including Kalman Filter, Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), Particle Filter (PF), and graph-based optimization. A multi-layer sensor fusion architecture combining odometry, inertial sensing, LiDAR, and vision-based observations is proposed for accurate robot pose estimation in dynamic environments. Experimental results demonstrate that multi-sensor fusion significantly improves localization accuracy, reduces drift, enhances robustness against sensor failures, and increases adaptability in indoor environments. Metrics such as RMSE, trajectory consistency, heading accuracy, covariance stability, and computational efficiency were used for evaluation. The integration of LiDAR, IMU, and wheel odometry reduced localization error by over 90% compared to wheel odometry alone, while vision-based loop closure further improved map consistency. Overall, the study highlights that advanced sensor fusion techniques provide an effective and reliable solution for autonomous robot localization and continue to influence modern robotic navigation systems.
Carlos Hugo Ribeiro Mendes· International Journal of Int...· 0 citations
Simulation and physical experiments confirmed collision-free navigation and successful quick response (QR)-code-based goods inspection, demonstrating the feasibility of the proposed framework for small, structured indoor environments.
T. Q. Le, T. Luu· IAES International Journal o...· 0 citations
Accurate and robust localization remains the fundamental bottleneck for truly autonomous robotic systems, despite decades of progress in probabilistic estimation and SLAM. This paper provides a critical and comprehensive review of mobile robot localization across sensing modalities, estimation paradigms, and deployment domains, covering ground, aerial, and underwater platforms. Beyond a descriptive survey, we explicitly analyze the limitations and trade-offs of existing approaches. We introduce an updated taxonomy that spans classical proprioceptive and exteroceptive sensors, emerging technologies such as 4D imaging radar and event cameras, and infrastructure-based positioning systems including GNSS and Ultra-Wideband. We revisit the evolution of localization algorithms, from Bayesian filtering techniques (EKF, UKF, and particle filters) to modern graph-based SLAM frameworks and tightly coupled multi-sensor fusion systems. Particular emphasis is placed on the recent paradigm shift toward learning-based and neural implicit approaches, including NeRF-SLAM and Gaussian Splatting, highlighting both their transformative potential and their current impracticality for real-time deployment. Unlike previous surveys, this work provides a unified cross-domain perspective while critically examining scalability, robustness, computational cost, and real-world deployability. We identify key unresolved challenges, including long-term consistency, operation in degraded environments, and the integration of semantic understanding into localization pipelines. Furthermore, we propose standardizing evaluation metrics with a formal Trajectory Completeness formulation to expose tracking brittleness. Finally, we outline future research directions toward resilient, certifiable, and truly autonomous localization systems, emphasizing the critical transition from passive estimation to Active SLAM in unstructured environments.
José Miguel Guerrero Guerrero Hernández, Rodrigo Pérez-Rodríguez, Juan S. Cely G. et al.· Robotics· 0 citations
Complex and dynamic environment autonomy, the ability to navigate complex and dynamic environments autonomously in real-time and with limited computational power, will persist as a basic challenge to mobile robotic systems. As a solution to this problem, this paper presents an alternative minimum-cost deep learning format using optimization, which combines a Modified Rime Optimization Algorithm (M-RIME) and a lightweight SqueezeNet-based navigation network. The given strategy is supposed to increase the depth of perception, precision of motion control, and computational efficiency at the same time. To begin with, an end-to-end navigation model that uses SqueezeNet is created to concurrently map raw red–green–blue observations to continuous motion commands to facilitate the perception–action interface. Subsequently, the M-RIME algorithm is improved with adaptive exploration–exploitation balancing and an adaptive mutation operator that greatly enhance convergence speed, global exploration, and the stability of solutions. The presented optimizer is used to improve the performance of the SqueezeNet model by automatically optimizing its hyperparameters within an offline optimization system, which improves navigation and retains its real-time functionality. Multi-frame and multi-measurement simulation experiments are performed in complex indoor navigation environments, where success rate, collision rate, navigation time, path length, and frames per second are adopted as quantitative and qualitative metrics to evaluate the suggested framework. The findings show that the optimized SqueezeNet is not only much better than the baseline model and other state-of-the-art optimization frameworks in terms of success rates of navigation, smoother trajectories, lower rates of collisions, and high-quality real-time optimization but also significantly better. In addition, convergence analysis establishes the effectiveness and precision of the suggested M-RIME algorithm in a high-dimensional optimization setting. On the whole, the presented framework will offer a good and scalable choice for autonomous navigation in real-time and can serve as an excellent basis for future developments aimed at temporal modeling, practical applications of autonomous driving, and multi-sensor fusion-driven robotic perception systems.
Jiangjun Ruan, Mei Wang, Lu Peng et al.· AIP Advances· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
