Shujing Zhang

AUV SLAM and Experiments Using a Mechanical Scanning Forward-Looking Sonar

Navigation technology is one of the most important challenges in the applications of autonomous underwater vehicles (AUVs) which navigate in the complex undersea environment. The ability of localizing a robot and accurately mapping its surroundings simultaneously, namely the simultaneous localization and mapping (SLAM) problem, is a key prerequisite of truly autonomous robots. In this paper, a modified-FastSLAM algorithm is proposed and used in the navigation for our C-Ranger research platform, an open-frame AUV. A mechanical scanning imaging sonar is chosen as the active sensor for the AUV. The modified-FastSLAM implements the update relying on the on-board sensors of C-Ranger. On the other hand, the algorithm employs the data association which combines the single particle maximum likelihood method with modified negative evidence method, and uses the rank-based resampling to overcome the particle depletion problem. In order to verify the feasibility of the proposed methods, both simulation experiments and sea trials for C-Ranger are conducted. The experimental results show the modified-FastSLAM employed for the navigation of the C-Ranger AUV is much more effective and accurate compared with the traditional methods.

Autonomous navigation for autonomous underwater vehicles based on information filters and active sensing.

This paper addresses an autonomous navigation method for the autonomous underwater vehicle (AUV) C-Ranger applying information-filter-based simultaneous localization and mapping (SLAM), and its sea trial experiments in Tuandao Bay (Shangdong Province, P.R. China). Weak links in the information matrix in an extended information filter (EIF) can be pruned to achieve an efficient approach-sparse EIF algorithm (SEIF-SLAM). All the basic update formulae can be implemented in constant time irrespective of the size of the map; hence the computational complexity is significantly reduced. The mechanical scanning imaging sonar is chosen as the active sensing device for the underwater vehicle, and a compensation method based on feedback of the AUV pose is presented to overcome distortion of the acoustic images due to the vehicle motion. In order to verify the feasibility of the navigation methods proposed for the C-Ranger, a sea trial was conducted in Tuandao Bay. Experimental results and analysis show that the proposed navigation approach based on SEIF-SLAM improves the accuracy of the navigation compared with conventional method; moreover the algorithm has a low computational cost when compared with EKF-SLAM.

Fast Image Recognition Based on Independent Component Analysis and Extreme Learning Machine

Abstract Nowadays, image recognition has become a highly active research topic in cognitive computation community, due to its many potential applications. Generally, the image recognition task involves two subtasks: image representation and image classification. Most feature extraction approaches for image representation developed so far regard independent component analysis (ICA) as one of the essential means. However, ICA has been hampered by its extremely expensive computational cost in real-time implementation. To address this problem, a fast cognitive computational scheme for image recognition is presented in this paper, which combines ICA and the extreme learning machine (ELM) algorithm. It tries to solve the image recognition problem at a much faster speed by using ELM not only in image classification but also in feature extraction for image representation. As an example, our proposed approach is applied to the face image recognition with detailed analysis. Firstly, common feature hypothesis is introduced to extract the common visual features from universal images by the traditional ICA model in the offline recognition process, and then ELM is used to simulate ICA for the purpose of facial feature extraction in the online recognition process. Lastly, the resulting independent feature representation of the face images extracted by ELM rather than ICA will be fed into the ELM classifier, which is composed of numerous single hidden layer feed-forward networks. Experimental results on Yale face database and MNIST digit database have shown the good performance of our proposed approach, which could be comparable to the state-of-the-art techniques at a much faster speed.

A Novel Combined SLAM Based on RBPF-SLAM and EIF-SLAM for Mobile System Sensing in a Large Scale Environment

Mobile autonomous systems are very important for marine scientific investigation and military applications. Many algorithms have been studied to deal with the computational efficiency problem required for large scale Simultaneous Localization and Mapping (SLAM) and its related accuracy and consistency. Among these methods, submap-based SLAM is a more effective one. By combining the strength of two popular mapping algorithms, the Rao-Blackwellised particle filter (RBPF) and extended information filter (EIF), this paper presents a Combined SLAM—an efficient submap-based solution to the SLAM problem in a large scale environment. RBPF-SLAM is used to produce local maps, which are periodically fused into an EIF-SLAM algorithm. RBPF-SLAM can avoid linearization of the robot model during operating and provide a robust data association, while EIF-SLAM can improve the whole computational speed, and avoid the tendency of RBPF-SLAM to be over-confident. In order to further improve the computational speed in a real time environment, a binary-tree-based decision-making strategy is introduced. Simulation experiments show that the proposed Combined SLAM algorithm significantly outperforms currently existing algorithms in terms of accuracy and consistency, as well as the computing efficiency. Finally, the Combined SLAM algorithm is experimentally validated in a real environment by using the Victoria Park dataset.

A modified FastSLAM with simple particle swarm optimization and consistent mapping for AUVs

Searching an accurate and effective simultaneous localization and mapping (SLAM) algorithm is fundamental to autonomous underwater vehicles (AUVs) to perform robust autonomous navigation. FastSLAM is one of the most popular SLAM algorithms. In spite of its wide applications, it still suffers from two major drawbacks, inconsistency and particle degeneration. In this paper, a modified FastSLAM algorithm is proposed using First-Estimates Jacobian (FEJ) to obtain a more consistent map and innovatively applying simple particle swarm optimization (sPSO) to address the particle degeneration problem. The modified FastSLAM algorithm effectively improves the accuracy of navigation and enhances the consistency of estimation. The paper also evaluates the proposed method with our own research platform, C-Ranger AUV, through sea trials in Tuandao Bay. The results of simulation and sea trial reveal that the modified algorithm has better performance in terms of the accuracy and consistency compared with standard FastSLAM.

Autonomous Navigation with Constrained Consistency for C-Ranger

Autonomous underwater vehicles (AUVs) have become the most widely used tools for undertaking complex exploration tasks in marine environments. Their synthetic ability to carry out localization autonomously and build an environmental map concurrently, in other words, simultaneous localization and mapping (SLAM), are considered to be pivotal requirements for AUVs to have truly autonomous navigation. However, the consistency problem of the SLAM system has been greatly ignored during the past decades. In this paper, a consistency constrained extended Kalman filter (EKF) SLAM algorithm, applying the idea of local consistency, is proposed and applied to the autonomous navigation of the C-Ranger AUV, which is developed as our experimental platform. The concept of local consistency (LC) is introduced after an explicit theoretical derivation of the EKF-SLAM system. Then, we present a locally consistency-constrained EKF-SLAM design, LC-EKF, in which the landmark estimates used for linearization are fixed at the beginning of each local time period, rather than evaluated at the latest landmark estimates. Finally, our proposed LC-EKF algorithm is experimentally verified, both in simulations and sea trials. The experimental results show that the LC-EKF performs well with regard to consistency, accuracy and computational efficiency.

Efficient implementation of incremental smoothing and mapping based on fluid variable reordering for AUVs

Simultaneous localization and mapping (SLAM) has become a hot topic for autonomous underwater vehicles (AUVs) used in underwater applications. The most recent approach iSAM2 has been successfully applied in large-scale environment. In order to choose a good variable ordering for the efficiency of the sparse matrix solution, iSAM2 uses a strategy called incremental variable reordering. However, applying this strategy at every incremental update increases the computational cost. So in this paper, we innovatively improve iSAM2 algorithm by introducing fluid variable reordering. The variables reordering is need to be done only at necessary steps decided through a multi-restraint loop-closure detection method. The proposed method is applied on our own research platform, C-Ranger AUV, through sea trials in Tuandao Bay. The results from simulation and sea trial demonstrate the feasibility of the proposed method and reveal that the modified iSAM2 algorithm has lower computational cost and keeps a highly accurate estimation.

An efficient digital image compression scheme based on ICA for underwater color images

As one of the dominant techniques for sensing the underwater environments, underwater vision has shown great prospects in ocean investigations and explorations over the last decades. The vision system is usually installed on the platforms of autonomous underwater vehicles (AUVs). Due to the limitation of transmission and storage for underwater signals, it is extremely urgent to explore an efficient digital image compression approach for underwater color images. In this paper, an efficient digital image compression scheme based on independent component analysis (ICA) is proposed to deal with the redundancy reduction problem for underwater color images, taking account of the acceptable perceptual quality of reconstructed images.

ICM: An efficient data association for SLAM in stochastic mapping

In this paper, iterative classification matching (ICM), a novel practical data association method, is proposed. ICM is an iterative approach to solve the data association problem which reconsiders the established observation-feature pairing and applies the quaternion approach to yield a least squares matching vector. The map features which are not associated with any observations are updated then by the obtained least squares matching vector to weaken the influence of the inaccurate vehicle pose estimation. Finally, the updated feature set and the unassociated observations are taken as a group of new inputs to perform the iteration again. The iteration is terminated until the discrepancy in mean square error falls below a preset threshold specifying the desired precision of the matching. Results of simulation experiments show that the proposed ICM method is an efficient solution to data association. Unlike ICNN (individual compatibility nearest neighbor), ICM can provide a robust solution in both simulated and real outdoor environments. Simultaneously, the computational cost of the proposed ICM algorithm is much lower than JCBB (joint compatibility branch and bound).