Many swarm optimization algorithms have been introduced since the early 60’s, Evolutionary Programming to the most recent, Grey Wolf Optimization. All of these algorithms have demonstrated their potential to solve many optimization problems. This paper provides an in-depth survey of well-known optimization algorithms. Selected algorithms are briefly explained and compared with each other comprehensively through experiments conducted using thirty well-known benchmark functions. Their advantages and disadvantages are also discussed. A number of statistical tests are then carried out to determine the significant performances. The results indicate the overall advantage of Differential Evolution (DE) and is closely followed by Particle Swarm Optimization (PSO), compared with other considered approaches.

/pdf/a-comprehensive-review-of-swarm-optimization-algorithms-34u47p9l9e.pdf

A Comprehensive Review of Swarm Optimization Algorithms

The key objective of unmanned aerial vehicle (UAV) path planning is to produce a flight path that connects a start state and a goal state while meeting the required constraints. Computational intelligence (CI) is a set of nature-inspired computational methodologies and approaches for addressing complex real-world problems for which mathematical or traditional modelling does not perform well. It has been applied in the field of UAVs since it can yield effective, accurate and rapid solutions. This article provides an overview of studies on UAV path planning based on CI methods published in major journals and conference proceedings. We survey relevant studies with respect to different CI algorithms utilized in UAV path planning, the types of time domain in UAV path planning, namely, offline and online, and the types of environment models, namely, 2D and 3D. It is observed that CI methods outperform traditional methods on online and 3D problems. The analysis is useful for identifying key results from UAV path planning research and is leveraged in this article to highlight trends and open issues.

Survey on computational-intelligence-based UAV path planning

In this paper, we propose a deep reinforcement learning (DRL)-based method that allows unmanned aerial vehicles (UAVs) to execute navigation tasks in large-scale complex environments. This technique is important for many applications such as goods delivery and remote surveillance. The problem is formulated as a partially observable Markov decision process (POMDP) and solved by a novel online DRL algorithm designed based on two strictly proved policy gradient theorems within the actor-critic framework. In contrast to conventional simultaneous localization and mapping-based or sensing and avoidance-based approaches, our method directly maps UAVs’ raw sensory measurements into control signals for navigation. Experiment results demonstrate that our method can enable UAVs to autonomously perform navigation in a virtual large-scale complex environment and can be generalized to more complex, larger-scale, and three-dimensional environments. Besides, the proposed online DRL algorithm addressing POMDPs outperforms the state-of-the-art.

Autonomous Navigation of UAVs in Large-Scale Complex Environments: A Deep Reinforcement Learning Approach

Ieee transactions® on aerospace and electronic systems

An innovative information fusion method with adaptive Kalman filter for integrated INS/GPS navigation of autonomous vehicles

Simultaneous Localization and Mapping (SLAM) based on LIDAR and MEMS IMU is a kind of autonomous integrated navigation technology. It can provide attitude, velocity position for a small UAV in an indoor frame during the outage of GNSS. A method of integrating the measurements from a LIDAR and a MEMS IMU was proposed in the paper. LIDAR measurements are a set of ranges and scan angles. The angle rates and accelerations from MEMS IMU are used to drive the simplified strapdown INS equations. The first step of the method is environment features extracting from the measurements of LIDAR and constructing a feature map. Then, the model of errors of LIDAR measurement due to the change of the scan plane during the attitude manoeuver is established and compensated based on aiding information from MEMS INS and the assumption about the structural indoor environment. The relative position parameters derived from environmental features delay matching algorithm and the differences of measurements of LIDAR at adjacent times are used to estimate the error of MEMS INS and MEMS sensors by a Kaiman Filter. A LIDAR/MEMS IMU prototype was designed to verify the practicability of the integrated navigation system of LIDAR and MEMS IMU. Some experiments were carried out in a room and the results demonstrated the potential use of the LIDAR/MEMS IMU integration navigation system.

LIDAR/MEMS IMU integrated navigation (SLAM) method for a small UAV in indoor environments

A fault-detection algorithm for a redundant multisensor navigation system for hypersonic cruise vehicles (HCVs) is proposed. The algorithm comprehensively diagnoses failures according to the failure level monitored by the sequential probability ratio test (SPRT) and chi-square test as well as the failure trend monitored by the SPRT. A test statistics feedback-reset loop is also added to shorten the recovery time after failure ceases. Simulations indicate improvements in both failure detection and recovery speed, contributing to improved accuracy and stability in HCV fault-tolerant navigation.

Chi-square and SPRT combined fault detection for multisensor navigation

A new dynamic vector formed information sharing algorithm in federated filter

An adaptive cubature Kalman filter algorithm for inertial and land-based navigation system

With the development of global navigation satellite system (GNSS), the GNSS/inertial navigation system (INS) integrated system offers the users better positioning or navigation performance. This paper proposes an adaptive robust ultra-tightly coupled GNSS/INS system based on a novel vector tracking strategy for combining both global positioning system (GPS) L1 and BeiDou B1 signals' tracking together. The inherent mechanism of the vector tracking approach has been analysed to describe the relationship between the replica signals and user's dynamic state. Then, an adaptive robust filter is used to gain the accurate estimates of vehicle states when the vehicle is under a weak-signal or large manoeuvring environment. Finally, the experimental platform is set up using a GPS/BeiDou signal simulator and an inertial measurement unit simulator and the test results show that the proposed ultra-tightly coupled system can keep the tracking loops from the high dynamic perturbations, which saves the cost time of signal reacquisition. Moreover, the presented adaptive robust ultra-tightly coupled system can obtain a higher accuracy than Kalman filtering in a simultaneous weak-signal and large manoeuvring environment.

Adaptive robust ultra-tightly coupled global navigation satellite system/inertial navigation system based on global positioning system/BeiDou vector tracking loops

Jianye Liu

Papers

LIDAR/MEMS IMU integrated navigation (SLAM) method for a small UAV in indoor environments

Chi-square and SPRT combined fault detection for multisensor navigation

A new dynamic vector formed information sharing algorithm in federated filter

An adaptive cubature Kalman filter algorithm for inertial and land-based navigation system

Adaptive robust ultra-tightly coupled global navigation satellite system/inertial navigation system based on global positioning system/BeiDou vector tracking loops