Laser-based Simultaneous Localization And Mapping Research Articles

Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM.

This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive Simultaneous Localization and Mapping (SLAM), where we often need to distinguish between the static parts of the environment with respect to which we localize the vehicle, and non-stationary objects that should not be included in the map for localization. Non-stationary objects do not provide repeatable readouts, because they can be in motion, like vehicles and pedestrians, or because they do not have a rigid, stable surface, like trees and lawns. The proposed approach exploits images synthesized from the received intensity data yielded by the modern LiDARs along with the usual range measurements. We demonstrate that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process. This concept makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non-stationary objects. The point clouds are filtered using the corresponding intensity images with labeled pixels. Finally, we demonstrate that the detection of non-stationary objects using our approach improves the localization results and map consistency in a laser-based SLAM system.

Visual Features Assisted Robot Localization in Symmetrical Environment Using Laser SLAM.

Localization for estimating the position and orientation of a robot in an asymmetrical environment has been solved by using various 2D laser rangefinder simultaneous localization and mapping (SLAM) approaches. Laser-based SLAM generates an occupancy grid map, then the most popular Monte Carlo Localization (MCL) method spreads particles on the map and calculates the position of the robot by a probabilistic algorithm. However, this can be difficult, especially in symmetrical environments, because landmarks or features may not be sufficient to determine the robot’s orientation. Sometimes the position is not unique if a robot does not stay at the geometric center. This paper presents a novel approach to solving the robot localization problem in a symmetrical environment using the visual features-assisted method. Laser range measurements are used to estimate the robot position, while visual features determine its orientation. Firstly, we convert laser range scans raw data into coordinate data and calculate the geometric center. Secondly, we calculate the new distance from the geometric center point to all end points and find the longest distances. Then, we compare those distances, fit lines, extract corner points, and calculate the distance between adjacent corner points to determine whether the environment is symmetrical. Finally, if the environment is symmetrical, visual features based on the ORB keypoint detector and descriptor will be added to the system to determine the orientation of the robot. The experimental results show that our approach can successfully determine the position of the robot in a symmetrical environment, while ordinary MCL and its extension localization method always fail.

Modelling, Simulation, and Implementing ROS for Autonomous Navigation of Tracked Robot

This paper presents autonomous navigation and its implementation based on Robotic Operating System (ROS) for a non-holonomic autonomous tracked robot, whereas it handles a full design, implementation, dynamic modeling, and kinematic modeling of the robot. This paper applies robot localization using Adaptive Monte Carlo Localization (AMCL) which uses a particle filter to track the pose of a robot against a known map. It also uses mapping based on the mapping package. It provides laser-based SLAM (Simultaneous Localization and Mapping) mapping. The LIDAR is used to create a 2-D occupancy grid map. Path planning is established using the Dijkstra algorithm to plan a path to a goal position, using a persistent map created by the robot during the mapping process. Also, the robot was equipped with a camera module for image processing and detection of different objects for security purposes. The proposed system shows its capability for adaptation to road segments of different curvatures and the transitions between them.

Lidar-based system for high-precision localization and real-time 3D map construction

Simultaneous localization and mapping (SLAM) is considered as the core of building high-precision three-dimensional environmental maps. For this, we proposed a high-precision laser-based SLAM system. Aiming at the problem that the point cloud data obtained from laser is not representative and the iterative closest point method for calculating pose transformation is time-consuming, we proposed an efficient and stable matching algorithm. It uses fused feature points to align with the occupancy grid submaps with less registration error and is less time-consuming. Then, to address the problem in which the registration result falls into the local optimum early, we proposed a quadratic registration algorithm. This method effectively improves the initial value of the registration process. Finally, a time consistency and global consistency loop detection algorithm are used to reduce the cumulative error. The system we proposed has been tested on the University of Michigan North Campus Long-Term dataset and Cartographer dataset. Experiments show that our system has good accuracy under low-speed motion conditions (speeds ranging from 1 to 2 m / s).

GP-SLAM: laser-based SLAM approach based on regionalized Gaussian process map reconstruction

Existing laser-based 2D simultaneous localization and mapping (SLAM) methods exhibit limitations with regard to either efficiency or map representation. An ideal method should estimate the map of the environment and the state of the robot quickly and accurately while providing a compact and dense map representation. In this study, we develop a new laser-based SLAM algorithm by redesigning the two core elements common to all SLAM systems, namely the state estimation and map construction. Utilizing Gaussian process (GP) regression, we propose a new type of map representation based on the regionalized GP map reconstruction algorithm. With this new map representation, both the state estimation method and the map update method can be completed with the use of concise mathematics. For small- or medium-scale scenarios, our method, consisting of only state estimation and map construction, demonstrates outstanding performance relative to traditional occupancy-grid-map-based approaches in both accuracy and especially efficiency. For large-scale scenarios, we extend our approach to a graph-based version.

POU-SLAM: Scan-to-Model Matching Based on 3D Voxels

Purpose: Localization and mapping with LiDAR data is a fundamental building block for autonomous vehicles. Though LiDAR point clouds can often encode the scene depth more accurate and steadier compared with visual information, laser-based Simultaneous Localization And Mapping (SLAM) remains challenging as the data is usually sparse, density variable and less discriminative. The purpose of this paper is to propose an accurate and reliable laser-based SLAM solution. Design/methodology/approach: The method starts with constructing voxel grids based on the 3D input point cloud. These voxels are then classified into three types to indicate different physical objects according to the spatial distribution of the points contained in each voxel. During the mapping process, a global environment model with Partition of Unity (POU) implicit surface is maintained and the voxels are merged into the model from stage to stage, which is implemented by Levenberg–Marquardt algorithm. Findings: We propose a laser-based SLAM method. The method uses POU implicit surface representation to build the model and is evaluated on the KITTI odometry benchmark without loop closure. Our method achieves around 30% translational estimation precision improvement with acceptable sacrifice of efficiency compared to LOAM. Overall, our method uses a more complex and accurate surface representation than LOAM to increase the mapping accuracy at the expense of computational efficiency. Experimental results indicate that the method achieves accuracy comparable to the state-of-the-art methods. Originality/value: We propose a novel, low-drift SLAM method that falls into a scan-to-model matching paradigm. The method, which operates on point clouds obtained from Velodyne HDL64, is of value to researchers developing SLAM systems for autonomous vehicles.

A novel edge-enabled SLAM solution using projected depth image information

Environmental mapping is the key step for mobile robots to perform tasks independently and perfectly. In recent years, visual SLAM, laser-based SLAM and simultaneous localization and mapping (SLAM) have aroused the interest of many people. Unfortunately, those technologies are not widely used, limited by the computational complexity, data processing and very low and predictable latency. This paper had mainly completed the following work and edge-enabled computing-based edge computing (Shi and Dustdar in Computer 49(5):78–81, 2016) is used as a solution to accelerate calculation. First of all, this research design works with inertial unit mobile robotic navigation systems, and all sensors are connected in edge layers in the framework of edge computing and explore the accelerometer, electronic compass, and gyroscope data. The accelerometer data are integrated using the Kalman filter data fusion algorithm to filter the random drift error caused by the gyroscope and the electronic compass. The state of the machine is determined by calculation of the corresponding attitude angle and position information. Second, a low-cost distance sensor is used to detect the depth and upload to the other fog node for computation. Next, the 3D point coordinate information is projected onto the two-dimensional coordinate extraction feature point to establish the feature map. Third, the extended Kalman filter SLAM is used to achieve simultaneous positioning and mapping. Finally, the method is validated in the experiment, proving that the method is feasible. The main improvement in this article is as follows: First, the multi-sensor data fusion algorithm is used to reduce the positioning error. Second, we use low-cost distance sensors to measure the depth of the model environment and reduce the cost. Third, we would take advantage of translating the three-dimensional depth information into a flat two-dimensional projection information to reduce the calculation of load and computing time. Fourth, our computation is distributed in different layers and focuses on edge-enabled platform to decrease the latency and redundancy.

An Eight-Direction Scanning Detection Algorithm for the Mapping Robot Pathfinding in Unknown Indoor Environment.

Aiming at the problem of how to enable the mobile robot to navigate and traverse efficiently and safely in the unknown indoor environment and map the environment, an eight-direction scanning detection (eDSD) algorithm is proposed as a new pathfinding algorithm. Firstly, we use a laser-based SLAM (Simultaneous Localization and Mapping) algorithm to perform simultaneous localization and mapping to acquire the environment information around the robot. Then, according to the proposed algorithm, the 8 certain areas around the 8 directions which are developed from the robot’s center point are analyzed in order to calculate the probabilistic path vector of each area. Considering the requirements of efficient traverse and obstacle avoidance in practical applications, the proposal can find the optimal local path in a short time. In addition to local pathfinding, the global pathfinding is also introduced for unknown environments of large-scale and complex structures to reduce the repeated traverse. The field experiments in three typical indoor environments demonstrate that deviation of the planned path from the ideal path can be kept to a low level in terms of the path length and total time consumption. It is confirmed that the proposed algorithm is highly adaptable and practical in various indoor environments.

Indoor laser-based SLAM for micro aerial vehicles

This article presents a laser-based 2D simultaneous localization and mapping (SLAM) algorithm for indoor environments. An adaption and optimization of a ground vehicle SLAM solution (TinySLAM) for the use with Micro Aerial Vehicles is proposed. Optimizations of the map update strategy and a motion model improves the accuracy strongly. An extension to 3D mapping is introduced. The presented algorithm is tested with simulated and real world data. The optimized SLAM solution maps a whole floor of an office building very accurately and achieves embedded real-time capability.

Information-theoretic compression of pose graphs for laser-based SLAM

In graph-based simultaneous localization and mapping (SLAM), the pose graph grows over time as the robot gathers information about the environment. An ever growing pose graph, however, prevents long-term mapping with mobile robots. In this paper, we address the problem of efficient information-theoretic compression of pose graphs. Our approach estimates the mutual information between the laser measurements and the map to discard the measurements that are expected to provide only a small amount of information. Our method subsequently marginalizes out the nodes from the pose graph that correspond to the discarded laser measurements. To maintain a sparse pose graph that allows for efficient map optimization, our approach applies an approximate marginalization technique that is based on Chow–Liu trees. Our contributions allow the robot to effectively restrict the size of the pose graph. Alternatively, the robot is able to maintain a pose graph that does not grow unless the robot explores previously unobserved parts of the environment. Real-world experiments demonstrate that our approach to pose graph compression is well suited for long-term mobile robot mapping.