Trainable Quaternion Extended Kalman Filter with Multi-Head Attention for Dead Reckoning in Autonomous Ground Vehicles.

Extended Kalman filter (EKF) is one of the most widely used Bayesian estimation methods in the optimal control area. Recent works on mobile robot control and transportation systems have applied various EKF methods, especially for localization. However, it is difficult to obtain adequate and reliable process-noise and measurement-noise models due to the complex and dynamic surrounding environments and sensor uncertainty. Generally, the default noise values of the sensors are provided by the manufacturer, but the values may frequently change depending on the environment. Thus, this paper mainly focuses on designing a highly accurate trainable EKF-based localization framework using inertial measurement units (IMUs) for the autonomous ground vehicle (AGV) with dead reckoning, with the goal of fusing it with a laser imaging, detection, and ranging (LiDAR) sensor-based simultaneous localization and mapping (SLAM) estimation for enhancing the performance. Convolution neural networks (CNNs), backward propagation algorithms, and gradient descent methods are implemented in the system to optimize the parameters in our framework. Furthermore, we develop a unique cost function for training the models to improve EKF accuracy. The proposed work is general and applicable to diverse IMU-aided robot localization models.

Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey.

Loop closure detection is of vital importance in the process of simultaneous localization and mapping (SLAM), as it helps to reduce the cumulative error of the robot's estimated pose and generate a consistent global map. Many variations of this problem have been considered in the past and the existing methods differ in the acquisition approach of query and reference views, the choice of scene representation, and associated matching strategy. Contributions of this survey are many-fold. It provides a thorough study of existing literature on loop closure detection algorithms for visual and Lidar SLAM and discusses their insight along with their limitations. It presents a taxonomy of state-of-the-art deep learning-based loop detection algorithms with detailed comparison metrics. Also, the major challenges of conventional approaches are identified. Based on those challenges, deep learning-based methods were reviewed where the identified challenges are tackled focusing on the methods providing long-term autonomy in various conditions such as changing weather, light, seasons, viewpoint, and occlusion due to the presence of mobile objects. Furthermore, open challenges and future directions were also discussed.

Semantics Aware Dynamic SLAM Based on 3D MODT.

The idea of SLAM (Simultaneous Localization and Mapping) being a solved problem revolves around the static world assumption, even though autonomous systems are gaining environmental perception capabilities by exploiting the advances in computer vision and data-driven approaches. The computational demands and time complexities remain the main impediment in the effective fusion of the paradigms. In this paper, a framework to solve the dynamic SLAM problem is proposed. The dynamic regions of the scene are handled by making use of Visual-LiDAR based MODT (Multiple Object Detection and Tracking). Furthermore, minimal computational demands and real-time performance are ensured. The framework is tested on the KITTI Datasets and evaluated against the publicly available evaluation tools for a fair comparison with state-of-the-art SLAM algorithms. The results suggest that the proposed dynamic SLAM framework can perform in real-time with budgeted computational resources. In addition, the fused MODT provides rich semantic information that can be readily integrated into SLAM.

Clothoid: An Integrated Hierarchical Framework for Autonomous Driving in a Dynamic Urban Environment.

In recent years, research and development of autonomous driving technology have gained much interest. Many autonomous driving frameworks have been developed in the past. However, building a safely operating fully functional autonomous driving framework is still a challenge. Several accidents have been occurred with autonomous vehicles, including Tesla and Volvo XC90, resulting in serious personal injuries and death. One of the major reasons is the increase in urbanization and mobility demands. The autonomous vehicle is expected to increase road safety while reducing road accidents that occur due to human errors. The accurate sensing of the environment and safe driving under various scenarios must be ensured to achieve the highest level of autonomy. This research presents Clothoid, a unified framework for fully autonomous vehicles, that integrates the modules of HD mapping, localization, environmental perception, path planning, and control while considering the safety, comfort, and scalability in the real traffic environment. The proposed framework enables obstacle avoidance, pedestrian safety, object detection, road blockage avoidance, path planning for single-lane and multi-lane routes, and safe driving of vehicles throughout the journey. The performance of each module has been validated in K-City under multiple scenarios where Clothoid has been driven safely from the starting point to the goal point. The vehicle was one of the top five to successfully finish the autonomous vehicle challenge (AVC) in the Hyundai AVC.

Dynamic Multi-LiDAR Based Multiple Object Detection and Tracking.

Environmental perception plays an essential role in autonomous driving tasks and demands robustness in cluttered dynamic environments such as complex urban scenarios. In this paper, a robust Multiple Object Detection and Tracking (MODT) algorithm for a non-stationary base is presented, using multiple 3D LiDARs for perception. The merged LiDAR data is treated with an efficient MODT framework, considering the limitations of the vehicle-embedded computing environment. The ground classification is obtained through a grid-based method while considering a non-planar ground. Furthermore, unlike prior works, 3D grid-based clustering technique is developed to detect objects under elevated structures. The centroid measurements obtained from the object detection are tracked using Interactive Multiple Model-Unscented Kalman Filter-Joint Probabilistic Data Association Filter (IMM-UKF-JPDAF). IMM captures different motion patterns, UKF handles the nonlinearities of motion models, and JPDAF associates the measurements in the presence of clutter. The proposed algorithm is implemented on two slightly dissimilar platforms, giving real-time performance on embedded computers. The performance evaluation metrics by MOT16 and ground truths provided by KITTI Datasets are used for evaluations and comparison with the state-of-the-art. The experimentation on platforms and comparisons with state-of-the-art techniques suggest that the proposed framework is a feasible solution for MODT tasks.

Range Sensor-Based Efficient Obstacle Avoidance through Selective Decision-Making.

In this paper, we address a collision avoidance method for mobile robots. Many conventional obstacle avoidance methods have been focused solely on avoiding obstacles. However, this can cause instability when passing through a narrow passage, and can also generate zig-zag motions. We define two strategies for obstacle avoidance, known as Entry mode and Bypass mode. Entry mode is a pattern for passing through the gap between obstacles, while Bypass mode is a pattern for making a detour around obstacles safely. With these two modes, we propose an efficient obstacle avoidance method based on the Expanded Guide Circle (EGC) method with selective decision-making. The simulation and experiment results show the validity of the proposed method.