Visual model‐predictive localization for computationally efficient autonomous racing of a 72‐g drone

Drone racing is becoming a popular e‐sport all over the world, and beating the best human drone race pilots has quickly become a new major challenge for artificial intelligence and robotics. In this paper, we propose a novel sensor fusion method called visual model‐predictive localization (VML). Within a small time window, VML approximates the error between the model prediction position and the visual measurements as a linear function. Once the parameters of the function are estimated by the RANSAC algorithm, this error model can be used to compensate the prediction in the future. In this way, outliers can be handled efficiently and the vision delay can also be compensated efficiently. Theoretical analysis and simulation results show the clear advantage compared with Kalman filtering when dealing with the occasional large outliers and vision delays that occur in fast drone racing. Flight tests are performed on a tiny racing quadrotor named “Trashcan,” which was equipped with a Jevois smart camera for a total of 72 g. An average speed of 2 m/s is achieved while the maximum speed is 2.6 m/s. To the best of our knowledge, this flying platform is currently the smallest autonomous racing drone in the world, while still being one of the fastest autonomous racing drones.     

A variable neighborhood search for flying sidekick traveling salesman problem

The efficiency and dynamism of unmanned aerial vehicles, or drones, have presented substantial application opportunities in several industries in the last years. Notably, logistic companies have given close attention to these vehicles to reduce delivery time and operational cost. A variant of the traveling salesman problem (TSP), called the flying sidekick traveling salesman problem, was introduced involving drone‐assisted parcel delivery. The drone launches from the truck, proceeds to deliver parcels to a customer, and then is recovered by the truck at a third location. While the drone travels through a trip, the truck delivers parcels to other customers as long as the drone has enough battery to hover waiting for the truck. This work proposes a hybrid heuristic where the initial solution is created from the optimal TSP solution reached by a TSP solver. Next, an implementation of the general variable neighborhood search is employed to obtain the delivery routes of truck and drone. Computational experiments show the potential of the algorithm to improve significantly delivery time. Furthermore, we provide a new set of instances based on the well‐known traveling salesman problem library instances.     

激光平面扫描3D测量系统快速标定技术

建立了激光平面扫描3D测量数学模型，提出了一种全新的3D测量系统参数的快速标定方法，设计了由2个完全垂直的平面组成的立体标定靶标，使用1个靶标可同时标定测量系统的摄像机参数和光平面方程参数。采用该方法对激光平面扫描测量系统进行了参数标定，用标定后的系统对标准平面进行了测量，空间测量精度优于0．1mm。     

无人机用森林灭火弹发射特性研究

为获得一种新型无人机用森林灭火弹的发射动力学特性,运用ANSYS-Workbench仿真软件建立无人机用森林灭火弹模型,讨论分析其前6阶的模态变化。为保证弹丸发射时的安全性,对无人机用森林灭火弹弹丸发射出膛时的瞬态动力学进行分析,为新型无人机用森林灭火弹的优化设计提供参考。结果表明：灭火弹发射出膛时弹丸的尾翼部最易发生形变,且出膛过程中弹丸在0.62 ms升至最大等效应力94 MPa,小于ABS工程塑料的许用应力,表明该无人机用森林灭火弹在最大应力下满足发射强度要求。     

Deep learning approach for investigation of temporal radio frequency signatures of drones

The omnipresence of drones in the civilian air space has led to their malicious usage raising high alert security issues. In this paper, a deep learning approach to detect and identify drones and to determine their flight modes from the remotely sensed radio frequency (RF) signatures is presented. This work intends to detect the presence of drones using two-class classification, the presence along with identification of their make using four-class classification. And this is further extended to the determination of their flight modes using ten-class classification. It employs the proposed architectures of prominent deep learning classifiers, namely, autoencoder (AE), long short-term memory (LSTM), convolutional neural network (CNN), and CNN-LSTM hybrid model. To procure the relevant information from 227 RF signatures having 100 fragments each, the seven significant temporal statistical features, namely, maxima, minima, mean, variance, skewness, kurtosis, and root mean square, are extracted. In a two-class classification scenario, all considered classifiers perform near to idle, whereas in a four-class classification scenario, CNN performs best, followed by AE, CNN-LSTM, and LSTM, respectively. Moreover, in a ten-class classification scenario, AE far outperforms CNN, followed by LSTM and CNN-LSTM, respectively. The best performance in terms of accuracy and classification time confirms the feasibility of the proposed AE classifier for the three considered drone operations.     

Cylindrical lithium-ion structural batteries for drones

The low cost, simplicity, and easy use of battery-powered multirotor aircraft has led to their adoption in commercial, industrial, agricultural, and military applications. These aircraft, however, have limited payloads and shorter endurance and range than fuel-powered conventional aircraft. To extend these key performance metrics, a structural battery is developed that uses commercially available battery cells as load bearing and power source elements for weight critical applications. The cylindrical structural battery is tested in three-point bending and is found to have four times higher stiffness and two times higher yield strength than the structure without battery reinforcement. Simulations of a quadcopter, redesigned with the proposed cylindrical structural batteries, demonstrate 41% longer hover time.     

Position control of a quadcopter drone using evolutionary algorithms-based self-tuning for first-order Takagi–Sugeno–Kang fuzzy logic autopilots

Trajectory tracking control of a quadcopter drone is a challenging work due to highly-nonlinear dynamics of the system, coupled with uncertainties in the flight environment (e.g. unpredictable wind gusts, measurement noise, modelling errors, etc). This paper addresses the aforementioned research challenges by proposing evolutionary algorithms-based self-tuning for first-order Takagi–Sugeno–Kang-type fuzzy logic controller (FLC). We consider three major state-of-the-art optimisation algorithms, namely, Genetic Algorithm, Particle Swarm Optimisation, and Artificial Bee Colony to facilitate automatic tuning. The effectiveness of the proposed control schemes is tested and compared under several different flight conditions, such as, constant, varying step and sine functions. The results show that the ABC-FLC outperforms the GA-FLC and PSO-FLC in terms of minimising the settling time in the absence of overshoots.     

消防救援队伍无人机飞手培养模式探讨

随着无人机在灭火救援中的不断拓展应用,消防救援队伍中无人机飞手严重短缺,如何有效培养拉得出、用得上、打得赢的实战型无人机飞手成为关键问题。通过对当前消防救援队伍中无人机飞手培养现状分析,结合国外消防部门的经验做法,探讨在现行体制下建立健全无人机飞手培养体系,加强和完善无人机飞手培养方法及模式,进一步提高消防救援队伍的中无人机飞手的实战救援能力。     

基于改进蚁群算法的水下无人机路径规划研究

为实现水下无人机在水域中自主作业的功能,对其设计一套合理的路径规划方案是非常有必要的。蚁群算法针对水下无人机路径规划方面有着非常好的效果,拥有不错的鲁棒性,但是传统的蚁群算法在解决路径规划问题时很容易出现局部最优解的问题。以传统蚁群遗传算法理论为根据,对其进行添加目标引导素、构建精英蚂蚁体系、更新信息素浓度这三方面的改进,使用栅格法构建水下环境分析模型,并以最短的路径为目的,规划一条从初始状态到目标状态的无碰安全途径,运用仿真的办法展开验证。结果显示：相较于传统算法,改进后的算法在求解速度和全局求解能力上有较大的优势。     

基于AFKF的多旋翼无人机组合导航技术研究

目前旋翼无人机组合导航系统大都使用扩展卡尔曼滤波算法,然而由于导航系统建模误差和传感器测量精度的影响,导航信息解算误差较大。为了改善旋翼无人机的飞行控制效果,应用自适应渐消卡尔曼滤波（Adaptive fading Kalman filter,AFKF）进行旋翼无人机组合导航解算,算法通过实时计算遗忘因子,对过去的数据权重进行削减,以提高扩展卡尔曼滤波算法的自适应能力。应用旋翼无人机真实飞行数据进行仿真,仿真结果表明,自适应渐消卡尔曼滤波算法能够有效抑制建模误差,弥补传感器测量精度不足,改善旋翼无人机组合导航解算结果。