Robust 2D map building with motion-free ICP algorithm for mobile robot navigation

A new three-dimensional (3D) map building method based on Laser Range Finder (LRF) has been proposed in this research, performing a surface estimation with the Iterative Closest Point (ICP) algorithm. While a mobile robot is navigating in an unknown environment, the entire environment cannot be scanned by LRF since kinematic features of the mobile robot and surface conditions are dynamically changing. To resolve this difficulty in building a 3D map while the mobile robot is navigating, a surface estimation ICP algorithm is proposed, which is based on the continuity of the environment around mobile robot. That is, this new algorithm recovers the un-scanned area by estimating feature points in the neighboring two regions based on the continuous environment information. The effectiveness of proposed algorithm has been demonstrated through real experiments of the mobile robot navigation.

The iterative closest point (ICP) algorithm is widely used in three-dimensional (3D) point cloud registration, and it is very stable and robust. However, its biggest drawback is being easily trapped in a local optimal solution, which results in the incorrect registration result. Currently, there is neither a clear effective range to define whether the ICP algorithm will fall into a local optimum nor a study providing a comprehensive evaluation of the ICP algorithm. In this paper, we take the overlap ratio, angle, distance, and noise as the influencing factors of ICP and evaluate the validity, robustness, accuracy, and efficiency of point-to-point and point-to-plane ICP by using four datasets. We first analyze the effective ranges of the two ICP algorithms with respect to overlap ratio, angle, and distance and then propose a universal effective range for the three factors. Next, the effect of Gaussian noise on the validity and accuracy of two ICPs is evaluated. We also analyze the factors influencing ICP accuracy and explain their changing rules. We finally study the effect of different parameters on the efficiency. All results are compared by using point-to-point and point-to-plane ICP algorithms. The results show that the overlap ratio has no effect on validity, but it has a significant influence on accuracy. The angle has a great impact on the validity and efficiency of ICP but has no effect on accuracy. The distance only affects validity, has a limited effect on efficiency and no effect on accuracy. Meanwhile, Gaussian noise has a little effect on the validity. In addition, the general effective range of point-to-point ICP is larger than that of point-to-plane ICP, but the point-to-plane ICP algorithm presents a better efficiency. The point-to-point ICP is more robust to Gaussian noise with respect to validity, while the point-to-plane is more resistant in terms of accuracy.

Artificial Potential Filed (APF) is the most well-known method that is used in mobile robot path planning, however, the shortcoming is that the local minima. To overcome this issue, we present a deadlock free APF based path planning algorithm for mobile robot navigation. The Proposed-APF (P-APF) algorithm searches the goal point in unknown 2D environments. This method is capable of escaping from deadlock and non-reachability problems of mobile robot navigation. In this method, the effective front-face obstacle information associated with the velocity direction is used to modify the Traditional APF (T-APF) algorithm. This modification solves the deadlock problem that the T-APF algorithm often converges to local minima. The proposed algorithm is explained in details and to show the effectiveness of the proposed approach, the simulation experiments were carried out in the MATLAB environment. Furthermore, the numerical analysis of the proposed approach is given to prove a deadlock free motion of the mobile robot.

Deep reinforcement learning methods have been applied to mobile robot navigation to find the optimal path to the target. The rewards are usually given when the task is completed, which may lead to the local optima during the training procedure. It seriously affects the training efficiency and navigation performance of the mobile robot. To this end, this paper proposes an intrinsic reward mechanism with intrinsic curiosity module and randomness enhanced module, combining the TD3 (twin-delayed deep deterministic policy gradient) reinforcement learning algorithm for mobile robot navigation. It effectively resolves the issue of slow convergence caused by sparse rewards in continuous action spaces. It also encourages mobile robots to explore unknown areas and reduces the occurrence of local optima. The experimental results show that the proposed navigation method significantly improves the training efficiency of mobile robots. Out of 1000 test episodes, only 3 exceeded the maximum step limit. This approach significantly reduces the occurrence of local optima. Furthermore, it increases the success rate to an impressive 83.5%, outperforms the existing navigation methods.

The Iterative Closest Point (ICP) is a matching technique used to determine the transformation matrix that best minimizes the distance between two point clouds. Although mostly used for 2D and 3D surface reconstruction, this technique is also widely used for mobile robot self-localization by means of matching partial information provided by an onboard LIDAR scanner with a known map of the facility. Once the estimated position of the robot is obtained, the scans gathered by the LIDAR can be analyzed to locate possible obstacles obstructing the planned trajectory of the mobile robot. This work proposes to speed up the obstacle detection process by directly monitoring outliers (discrepant points between the LIDAR scans and the full map) spotted after ICP matching instead of spending time performing an isolated task to re-analyze the LIDAR scans to detect those discrepancies. In this work, a computationally optimized ICP implementation has been adapted to return the list of outliers along with other matching metrics, computed in an optimal way by taking advantage of the parameters already calculated in order to perform the ICP matching. The evaluation of this adapted ICP implementation in a real mobile robot application has shown that the time required to perform self-localization and obstacle detection has been reduced by 36.7% when obstacle detection is performed simultaneously with the ICP matching instead of implementing a redundant procedure for obstacle detection. The adapted ICP implementation is provided in the SLAMICP library.

Main study areas for robotics research can be given as: mapping, localization, navigation and exploration. Given a robot’s current position, partial map of the environment and a goal position; navigation problem can be defined as optimal path planning and path following. Path planning and path following problem should be handled according to environment being static or dynamic, robot's mobility capabilities, sensors used on the robot and the roughness of the environment. In the study a four wheeled, skid-steering robot with laser range finder and depth sensor is built for Gazebo simulation environment. Also a statically structured labyrinth that consists of 15 degree continuous ramps, 15 degree discontinuous ramps, amorphous holes that robot cannot autonomously escape from if fallen into, walls and discontinuous obstacles that are below the robot laser height. 2D simultaneous localization and mapping, 3D mapping, path planning and path following with respect to the 3D map are implemented on Robot Operating System (ROS). Optimal path planning in rough terrain is accomplished by combining A* heuristic with a function of height difference of the 3D map nodes. Path following is carried out by turning-to and moving-towards actions on each sequential path node pairs. Tests performed on the labyrinth shows that obstacle avoidance, path planning and path following can be carried out successfully with the given implementation.

摘要: 为了实现移动机器人仅依靠激光测距仪和里程计实时地创建精确的栅格地图, 本文提出了一种结合最近点迭代(Iterative closest point, ICP)算法和Rao-Blackwellized粒子滤波的同时定位与地图创建方法. 该方法利用ICP算法对相邻两次激光扫描数据进行配准, 并将配准结果代替误差较大的里程计读数, 以改善基于里程计读数的建议分布函数; 同时通过采用改进的抽样策略, 提高了粒子滤波过程中的抽样效率, 降低创建地图所需的粒子数. 仿真结果表明了该方法的有效性. 关键词: 同时定位与地图创建 / 最近点迭代法 / Rao-Blackwellized粒子滤波 / 建议分布函数

The accuracy of the iterative closest point (ICP) algorithm, which is widely employed in image registration, depends on the complexity of the shape of the object under registration. Objects with complex features yield higher reliability in estimating registration parameters. For objects with rotation symmetry, a cylinder for example, rotation along the center axis can not be distinguished. We derive the sensitivity of the rotation error of the ICP algorithm from the curvature of the error function near the minimum error position. We approximate the defined error function to a second order polynomial and show that the coefficient of the second-order term is related to the reliability of the estimated rotation angle. Also the coefficient is related to the shape of the object. In the known correspondence case, the reliability can be expressed by the second moment of the input image. Finally, we apply the sensitivity formula to a simple synthetic object and ellipses, and verify that the predicted orientation variance of the ICP algorithm is in good agreement with computer simulations.

Differential LiDAR (Light Detection and Ranging) from repeated surveys has recently emerged as an effective tool to measure three-dimensional (3D) change for applications, such as quantifying slip and spatially distributed warping associated with earthquake ruptures, and examining the spatial distribution of beach erosion after hurricane impact. Currently, the primary method for determining 3D change from LiDAR is through the use of the iterative closest point (ICP) algorithm and its variants. However, all current studies using ICP have assumed that all LiDAR points in the compared point clouds have uniform accuracy. This assumption is simplistic given that the error for each LiDAR point is variable, and dependent upon time varying factors such as target range, angle of incidence, and aircraft trajectory accuracy. Therefore, to rigorously determine spatial change, it would be ideal to model the random error for every LiDAR observation in the differential point cloud, and use these error estimates as apriori weights in the ICP algorithm. To test this approach, we implemented a rigorous LiDAR observation error propagation method to generate estimated random error for each point in a LiDAR point cloud, and then determine 3D displacements between two point clouds using an anisotropic weighted ICP (A-ICP) algorithm. The algorithm was evaluated by qualitatively and quantitatively comparing point clouds with synthetic fault ruptures between a uniform weight and anistropically weighted ICP algorithm. Then post-earthquake slip is estimated for the 2010 El Mayor-Cucapah Earthquake (EMC), using pre- and post-event LiDAR. Based on the analysis, Moving Window A-ICP is able to better estimate the synthetic surface ruptures, and provides a smoother estimate of actual displacement for the EMC earthquake.

For the 3D perception problem of mobile robots in unknown indoor environments, a practical approach to building 3D maps using a low-cost Kinect sensor is proposed. Successive frames of RGB-D information are captured during the robots movements. First, SIFT(Scale-invariant Feature Transform)detector is applied to color images for extracting and matching stable feature points. Then, combined with the GTM(Graph Transformation Matching) algorithm to eliminate the possible existence of false matching points and complete the initial registration, so as to estimate the rough relative transfer between the image frames. Finally, using the ICP(Iterative Closest Point) algorithm, the robot's motion parameters are continuously updated to update the robot posture, and based on this, the 3D map of the indoor environment is created based on the combination of depth information. Experimental results validate the feasibility and effectiveness of the approach

We discuss mobile robot navigation under linguistic instructions of a route. The instructions given to the robot describe the route using landmarks such as intersections, for example, “turn right at the 2nd intersection, and ….”However, it is difficult to give the robot landmark models so that it recognizes each landmark properly as a human does. We have already proposed an algorithm for mobile robot navigation, which verifies the result of landmark recognition considering the positional relationship among landmarks. In this paper, we describe the motion planning to acquire additional information effectively for navigation of the mobile robot equipped with a range sensor based on the algorithm, aiming at realizing the real robot navigation using the linguistic instructions. The environment is described by a graph based on skeletons of its free space. The motion of the robot is first roughly planned with the graph-based global map and then precisely planned with a geometric local sensory information. In experimental results using a real robot, the robot reached the goal specified by the instructions despite of errors in sensing and motion.

Bin picking is an important task in smart manufacturing and intelligent robotics. For a robot to pick or grip an object with a human-like gripping action, it needs to know the accurate 3D pose of the object. In this paper, we propose a method for estimating the 3D pose of a small ring-shaped object using infrared and depth images generated by a depth camera. The proposed method consists of two algorithm modules, the first to recognize an object in a 2D infrared image and the second to estimate the 3D pose by applying the ICP (iterative closest point) algorithm to 3D depth data. In the first module, we propose a method to generate a three-channel integrated image with features from the depth and infrared images. Next, we introduce a method for training an object detector based on deep-learning. Because the bin-picking test object in this paper is small and ring-shaped, it is difficult to detect and find 3D poses of individual objects when many such objects are piled up. We solved this problem with a depth-based filtering method. Using the filtered image, each object region is separated by the deep learning approach. In the second module, the ICP algorithm is employed to estimate the 3D pose of the ring object. We match a 3D reference model of the object and the real object using the point-to-point ICP algorithm. Performance of the proposed method is evaluated by using two different types of depth camera in the experiments.

The problem of aligning of 3D point data is the known registration task. The most popular registration algorithm is the Iterative Closest Point (ICP) algorithm. The traditional ICP algorithm is a fast and accurate approach for rigid registration between two point clouds but it is unable to handle affine case. Recently, extension of the ICP algorithm for composition of scaling, rotation, and translation is proposed. A generalized ICP version for an arbitrary affine transformation is also suggested. In this paper, a new iterative algorithm for registration of point clouds based on the point-to-plane ICP algorithm with affine transformations is proposed. At each iteration, a closed-form solution to the affine transformation is derived. This approach allows us to get a precise solution for transformations such as rotation, translation, and scaling. With the help of computer simulation, the proposed algorithm is compared with common registration algorithms.

Mobile robots have been making a significant contribution to the advancement of many sectors including automation of mining, space, surveillance, military, health, agriculture and many more. Safe and efficient navigation is a fundamental requirement of mobile robots, thus, the demand for advanced algorithms rapidly increased. Mobile robot navigation encompasses the following four requirements: perception, localization, pathplanning and motion control. Among those, path-planning is a vital part of a fast, secure operation. During the last couple of decades, many path-planning algorithms were developed. Despite most of the mobile robot applications being in dynamic environments, the number of algorithms capable of navigating robots in dynamic environments is limited. This paper presents a qualitative comparative study of the up-to-date mobile robot pathplanning methods capable of navigating robots in dynamic environments. The paper discusses both classical and heuristic methods including artificial potential field, genetic algorithm, fuzzy logic, neural networks, artificial bee colony, particle swarm optimization, bacterial foraging optimization, ant-colony and Agoraphilic algorithm. The general advantages and disadvantages of each method are discussed. Furthermore, the commonly used state-of-the-art methods are critically analyzed based on six performance criteria: algorithm's ability to navigate in dynamically cluttered areas, moving goal hunting ability, object tracking ability, object path prediction ability, incorporating the obstacle velocity in the decision, validation by simulation and experimentation. This investigation benefits researchers in choosing suitable path-planning methods for different applications as well as identifying gaps in this field.

This paper presents a new neural network based reactive navigation algorithm for wheeled mobile robots (WMR) in unstructured indoor environments. The mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment. This navigation algorithm is optimized by a user-defined objective function which minimizes the traveled distance to the goal position while avoiding obstacles. The network is trained through off-line learning followed by an on-line learning algorithm with guaranteed convergence. The performance of the proposed algorithm is verified over a variety of real unstructured indoor environments using an autonomous mobile robot platform.