UAV Autonomous Navigation for Wireless Powered Data Collection with Onboard Deep Q-Network

In a rechargeable wireless sensor network,utilizing the unmanned aerial vehicle(UAV)as a mobile base station(BS)to charge sensors and collect data effectively prolongs the network’s lifetime.In this paper,we jointly optimize the UAV’s flight trajectory and the sensor selection and operation modes to maximize the average data traffic of all sensors within a wireless sensor network(WSN)during finite UAV’s flight time,while ensuring the energy required for each sensor by wireless power transfer(WPT).We consider a practical scenario,where the UAV has no prior knowledge of sensor locations.The UAV performs autonomous navigation based on the status information obtained within the coverage area,which is modeled as a Markov decision process(MDP).The deep Q-network(DQN)is employed to execute the navigation based on the UAV position,the battery level state,channel conditions and current data traffic of sensors within the UAV’s coverage area.Our simulation results demonstrate that the DQN algorithm significantly improves the network performance in terms of the average data traffic and trajectory design.

Autonomous Navigation for Unmanned Aerial Vehicles Based on Chaotic Bionics Theory

In this paper a new reactive mechanism based on perception-action bionics for multi-sensory integration applied to Un- manned Aerial Vehicles (UAVs) navigation is proposed.The strategy is inspired by the olfactory bulb neural activity observed in rabbits subject to external stimuli.The new UAV navigation technique exploits the use of a multiscroll chaotic system which is able to be controlled in real-time towards less complex orbits,like periodic orbits or equilibrium points,considered as perceptive orbits.These are subject to real-time modifications on the basis of environment changes acquired through a Synthetic Aperture Radar (SAR) sensory system.The mathematical details of the approach are given including simulation results in a virtual en- vironment.The results demonstrate the capability of autonomous navigation for UAV based on chaotic bionics theory in com- plex spatial environments.

An Autonomous Navigation Methodology for a Pioneer 3DX Robot

Autonomous navigation is a complex challenge that involves the interpretation and analysis of information about the scenario to facilitate the cognitive processes of a robot to perform free trajectories in dynamic environments. To solve this, the paper introduces a Case-Based Reasoning methodology to endow robots with an efficient decision structure aiming of selecting the best maneuver to avoid collisions. In particular, Manhattan Distance was implemented to perform the retrieval process in CBR method. Four scenarios were depicted to run a set of experiments in order to validate the functionality of the implemented work. Finally, conclusions emphasize the advantages of CBR methodology to perform autonomous navigation in unknown and uncertain environments.

Mobile Robot Indoor Autonomous Navigation with Position Estimation Using RF Signal Triangulation

In the mobile robotic systems a precise estimate of the robot pose (Cartesian [x y] position plus orientation angle theta) with the intention of the path planning optimization is essential for the correct performance, on the part of the robots, for tasks that are destined to it, especially when intention is for mobile robot autonomous navigation. This work uses a ToF (Time-of-Flight) of the RF digital signal interacting with beacons for computational triangulation in the way to provide a pose estimative at bi-dimensional indoor environment, where GPS system is out of range. It’s a new technology utilization making good use of old ultrasonic ToF methodology that takes advantage of high performance multicore DSP processors to calculate ToF of the order about ns. Sensors data like odometry, compass and the result of triangulation Cartesian estimative, are fused in a Kalman filter in the way to perform optimal estimation and correct robot pose. A mobile robot platform with differential drive and nonholonomic constraints is used as base for state space, plants and measurements models that are used in the simulations and for validation the experiments.

Autonomous navigation method of satellite constellation based on adaptive forgetting factors

To address the problem that model uncertainty and unknown time-varying system noise hinder the filtering accuracy of the autonomous navigation system of satellite constellation,an autonomous navigation method of satellite constellation based on the Unscented Kalman Filter with Adaptive Forgetting Factors(UKF-AFF)is proposed.The process noise covariance matrix is estimated online with the strategy that combines covariance matching and adaptive adjustment of forgetting factors.The adaptive adjustment coefficient based on squared Mahalanobis distance of state residual is employed to achieve online regulation of forgetting factors,equipping this method with more adaptability.The intersatellite direction vector obtained from photographic observations is introduced to determine the constellation satellite orbit together with the distance measurement to avoid rank deficiency issues.Considering that the number of available measurements varies online with intersatellite visibility in practical applications such as time-varying constellation configurations,the smooth covariance matrix of state correction determined by innovation and gain is adopted and constructed recursively.Stability analysis of the proposed method is also conducted.The effectiveness of the proposed method is verified by the Monte Carlo simulation and comparison experiments.The estimation accuracy of constellation position and velocity of UKF-AFF is improved by 30%and 44%respectively compared to those of the extended Kalman filter,and the method proposed is also better than other several adaptive filtering methods in the presence of significant model uncertainty.

Deep-reinforcement-learning-based UAV autonomous navigation and collision avoidance in unknown environments

In some military application scenarios,Unmanned Aerial Vehicles(UAVs)need to perform missions with the assistance of on-board cameras when radar is not available and communication is interrupted,which brings challenges for UAV autonomous navigation and collision avoidance.In this paper,an improved deep-reinforcement-learning algorithm,Deep Q-Network with a Faster R-CNN model and a Data Deposit Mechanism(FRDDM-DQN),is proposed.A Faster R-CNN model(FR)is introduced and optimized to obtain the ability to extract obstacle information from images,and a new replay memory Data Deposit Mechanism(DDM)is designed to train an agent with a better performance.During training,a two-part training approach is used to reduce the time spent on training as well as retraining when the scenario changes.In order to verify the performance of the proposed method,a series of experiments,including training experiments,test experiments,and typical episodes experiments,is conducted in a 3D simulation environment.Experimental results show that the agent trained by the proposed FRDDM-DQN has the ability to navigate autonomously and avoid collisions,and performs better compared to the FRDQN,FR-DDQN,FR-Dueling DQN,YOLO-based YDDM-DQN,and original FR outputbased FR-ODQN.

Review of X-ray pulsar spacecraft autonomous navigation

This article provides a review on X-ray pulsar-based navigation(XNAV).The review starts with the basic concept of XNAV,and briefly introduces the past,present and future projects concerning XNAV.This paper focuses on the advances of the key techniques supporting XNAV,including the navigation pulsar database,the X-ray detection system,and the pulse time of arrival estimation.Moreover,the methods to improve the estimation performance of XNAV are reviewed.Finally,some remarks on the future development of XNAV are provided.

Real-Time Slice-to-Volume Registration-Based Autonomous Navigation for Robot-Assisted Thyroid Biopsy

With advancements in medical imaging and robotic technology,the idea of fully autonomous diagnosis and treatment has become appealing,from ethereal to tangible.Owing to its characteristics of non-invasiveness,non-radiation,and fast imaging speed,ultrasonography has been increasingly used in clinical practice,such as in obstetrics,gynecology,and surgical puncture.In this paper,we propose a real-time image-based visual servo control scheme using a hybrid slice-to-volume registration method.In this manner,the robot can autonomously locate the ultrasound probe to the desired posture according to preoperational planning,even in the presence of disturbances.The experiments are designed and conducted using a thyroid biopsy phantom model.The results show that the proposed scheme can achieve a refresh rate of up to 30 Hz and a tracking accuracy of(0.52±0.65)mm.

Research on High Precision Autonomous Navigation of Shared Balancing Vehicles Based on EKF-SLAM

In view of the technical difficulties of autonomous navigation in local areas,this paper proposes a high-precision autonomous navigation shared bal-ancing bike system based on EKF-SLAM.This system uses the EKF-SLAM algorithm in robot localization to achieve simultaneous localization and map con-struction using the extended Kalmanfilter.At the same time,GPS and IMU are also employed for absolute positioning,and point cloud matching is used for rel-ative positioning to achieve multisensor fusion positioning.For the convenience of users,this system uses the RNN-T model for speech recognition destinations.Through experimental verification,the EKF-SLAM-based autonomous naviga-tion technology proposed in this paper can meet the accurate localization service and can realize the function of high precision autonomous navigation and voice recognition of destinations for shared balancing vehicles in a local area.

Pico-satellite Autonomous Navigation with Magnetometer and Sun Sensor Data

This article presents a near-Earth satellite orbit estimation method for pico-satellite applications with light-weight and low-power requirements. The method provides orbit information autonomously from magnetometer and sun sensor, with an extended Kalman filter （EKF）. Real-time position/velocity parameters are estimated with attitude independently from two quantities： the measured magnitude of the Earth’s magnetic field, and the measured dot product of the magnetic field vector and the sun vector. To guarantee the filter’s effectiveness, it is recommended that the sun sensor should at least have the same level of accuracy as magnetometer. Furthermore, to reduce filter’s computation expense, simplification methods in EKF’s Jacobian calculations are introduced and testified, and a polynomial model for fast magnetic field calculation is developed. With these methods, 50% of the computation expense in dynamic model propagation and 80% of the computation burden in measurement model calculation can be reduced. Tested with simulation data and compared with original magnetometer-only methods, filter achieves faster convergence and higher accuracy by 75% and 30% respectively, and the suggested simplification methods are proved to be harmless to filter’s estimation performance.

Development of autonomous navigation system for rice transplanter

Rice transplanting requires the operator to manipulate the rice transplanter in straight trajectories.Various markers are proposed to help experienced drivers in keeping straightforward and parallel to the previous path,which are extremely boring in terms of large-scale fields.The objective of this research was to develop an autonomous navigation system that automatically guided a rice transplanter working along predetermined paths in the field.The rice transplanter used in this research was commercially available and originally manually-operated.An automatic manipulating system was developed instead of manual functions including steering,stop,going forward and reverse.A sensor fusion algorithm was adopted to integrate measurements of the Real-Time Kinematic Global Navigation Satellite System(RTK-GNSS)and Inertial Measurement Unit(IMU),and calculate the absolute moving direction under the UTM coordinate system.A headland turning control method was proposed to ensure a robust turning process considering that the rice transplanter featured a small turning radius and a relatively large slip rate at extreme steering angles.Experiments were designed and conducted to verify the performance of the newly developed autonomous navigation system.Results showed that both lateral and heading errors were less than 8 cm and 3 degrees,respectively,in terms of following straight paths.And headland turns were robustly executed according to the required pattern.

Development of autonomous navigation controller for agricultural vehicles

Agricultural vehicles are adopted to undertake farming tasks by traversing along crop rows in the field.Working quality depends significantly on the driving skills of the operator.Automatic guidance has been introduced into agriculture to achieve high-accuracy path tracking during the last decades,which contributes considerably to straight-line navigation.The objective of this research was to develop an autonomous navigation controller that allowed movement autonomy for various agricultural vehicles.Three wheel-type vehicles were used as the test platform featuring automatic steering,hydrostatic transmission and speed control,which included a rice transplanter,a high-clearance sprayer and a tractor.A dual-antenna RTK-GNSS receiver was attached to the vehicles to provide spatial information on both positioning and heading by using the RTX service from Trimble.A path planning method was proposed to create a straight-line reference path by giving two points,and the target path was determined according to the vehicle initial status and working assignment.Headland turning was comprehensively taken into account by listing different turn patterns in order to realize autonomous navigation at the headland.The navigation controller hardware was fabricated for program execution,data processing and information communication with peripherals.A human-machine interface was designed for the operator to complete basic setting,path planning and navigation control by providing controls.Field experiments were conducted to evaluate the performance and versatility of the newly developed autonomous navigation controller in guiding agricultural vehicles to follow straight paths and turn at the headland.Results showed that an appropriate turn pattern was automatically executed when finishing straight-line navigation.The lateral error in straight-line tracking was no more than 6 cm,6 cm and 5 cm for the rice transplanter,the high-clearance sprayer and the tractor,respectively.And the maximum lateral RMS error was 3.10 cm,4.75 cm,2.21 cm in terms of straight-line tracking,which indicated that the newly developed autonomous navigation controller was versatile and of high robustness in guiding various agricultural vehicles.

Behavior-based Autonomous Navigation and Formation Control of Mobile Robots in Unknown Cluttered Dynamic Environments with Dynamic Target Tracking

While different species in nature have safely solved the problem of navigation in a dynamic environment, this remains a challenging task for researchers around the world. The paper addresses the problem of autonomous navigation in an unknown dynamic environment for a single and a group of three wheeled omnidirectional mobile robots(TWOMRs). The robot has to track a dynamic target while avoiding dynamic obstacles and dynamic walls in an unknown and very dense environment. It adopts a behavior-based controller that consists of four behaviors: "target tracking", "obstacle avoidance", "dynamic wall following" and "avoid robots". The paper considers the problem of kinematic saturation. In addition, it introduces a strategy for predicting the velocity of dynamic obstacles based on two successive measurements of the ultrasonic sensors to calculate the velocity of the obstacle expressed in the sensor frame. Furthermore, the paper proposes a strategy to deal with dynamic walls even when they have U-like or V-like shapes. The approach can also deal with the formation control of a group of robots based on the leader-follower structure and the behavior-based control, where the robots have to get together and maintain a given formation while navigating toward the target, avoiding obstacles and walls in a dynamic environment. The effectiveness of the proposed approaches is demonstrated via simulation.

Autonomous navigation to quasi-periodic orbits near translunar libration points

Libration-point missions have been very useful and successful. Due to the unstable natures of most of these orbits, the long-time stationkeeping demands frequent maneuvers and precise orbit determinations. Earth-based tracking will have to undertake much more responsibilities with the increasing number of libration missions. An autonomous navigation system could offer a better way to decrease the need for Earth-based tracking. Nevertheless, when an autonomous navigation system is applied, there are three important factors affecting autonomous navigation accuracy, i.e., the accuracy of initial conditions, the accuracy of measurements, and the accuracy of onboard dynamics for propagation. This paper focuses on analyzing the influence from the third factor and finding an appropriate navigation dynamics, which can satisfy the requirement of estimation accuracy but not cause too much burden for onboard computation. When considering the restricted three-body model and the bicircular restricted four-body model as navigation dynamics, the astrin- gency is not shown during the simulations. Meanwhile, when considering the influences of the Sun＇s direct and indirect perturbations and the eccentricity of the Moon＇s orbit, a new navigation dynamic model with the standard ephemerides is proposed. The simulation shows the feasibility of the proposed model.

Q-Learning-Based Target Selection for Bearings-Only Autonomous Navigation

This paper presents a Q-learning-based target selection algorithm for spacecraft autonomous navigation using bearing observations of known visible targets.For the considered navigation system,the position and velocity of the spacecraft are estimated using an extended Kalman filter(EKF)with the measurements of inter-satellite line-of-sight(LOS)vectors obtained via an onboard star camera.This paper focuses on the selection of the appropriate target at each observation period for the star camera adaptively,such that the performance of the EKF is enhanced.To derive an effective algorithm,a Q-function is designed to select a proper observation region,while a U-function is introduced to rank the targets in the selected region.Both the Q-function and the U-function are constructed based on the sequence of innovations obtained from the EKF.The efficiency of the Q-learning-based target selection algorithm is illustrated via numerical simulations,which show that the presented algorithm outperforms the traditional target selection strategy based on a Cramer-Rao bound(CRB)in the case that the prior knowledge about the target location is inaccurate.

A Technical Framework for Selection of Autonomous UAV Navigation Technologies and Sensors

The autonomous navigation of an Unmanned Aerial Vehicle(UAV)relies heavily on the navigation sensors.The UAV’s level of autonomy depends upon the various navigation systems,such as state measurement,mapping,and obstacle avoidance.Selecting the correct components is a critical part of the design process.However,this can be a particularly difficult task,especially for novices as there are several technologies and components available on the market,each with their own individual advantages and disadvantages.For example,satellite-based navigation components should be avoided when designing indoor UAVs.Incorporating them in the design brings no added value to the final product and will simply lead to increased cost and power consumption.Another issue is the number of vendors on the market,each trying to sell their hardware solutions which often incorporate similar technologies.The aim of this paper is to serve as a guide,proposing various methods to support the selection of fit-for-purpose technologies and components whilst avoiding system layout conflicts.The paper presents a study of the various navigation technologies and supports engineers in the selection of specific hardware solutions based on given requirements.The selection methods are based on easy-to-follow flow charts.A comparison of the various hardware components specifications is also included as part of this work.

Research on Autonomous Orbit Determination of Navigation Satellite Based on Crosslink Range and Orientation Parameters Constraining

Autonomous navigation of navigation satellite is discussed. The method of auto-orbit determination using the erosslink range and orientation parameters constraining is put forward. On the basis of the analysis of its feasibility, some useful conclusions are given.

Autonomous optical navigation of Mars probe aided by one-way Doppler measurements in capture stage

The optical navigation errors of Mars probe in the capture stage depend closely on which targets are selected to be observed in the Mars system.As for this problem,an integrated navigation scheme is proposed wherein the optical observation is aided by one-way Doppler measurements.The errors are then analyzed respectively for the optical observation and one-way Doppler measurements.The real-time calculating scheme which exploits the extended Kalman filter(EKF)framework is designed for the integrated navigation.The simulation tests demonstrate that the errors of optical navigation,which select the Mars moon as the observation target,are relatively smaller than those in the Mars-orientation optical navigation case.On one hand,the integrated navigation errors do not depend on the selecting pattern of optical observation targets.On the other hand,the integrated navigation errors are significantly reduced as compared with those in the optical-alone autonomous navigation mode.

Study on autonomous satellite navigation from SHAR observations

This paper uses two navigation schemes to prove the potential of a novel autonomous orbit determination with stellar horizon atmospheric refraction measurements. Scheme one needs a single processor and uses an extended Kalman filter. The second scheme needs two parallel processors. One processor uses a hatched leastsquare initial state estimator and a high-precision dynamic state propagator. The other processor uses a real-time orbit predictor. Simulations have been executed respectively for three types （low/medial/high） of satellite orbits on which various numbers of stars are observed. The results show both schemes can autonomously determine the orbits with a considerable performance. The second scheme in general performs a little better than the first scheme.

Research on Visual Autonomous Navigation Indoor for Unmanned Aerial Vehicle

The aim of this paper is to study visual autonomous navigation of unmanned aerial vehicle (UAV) in indoor global positioning system (GPS) denied environment. The UAV platform of the autonomous navigation flight control system is designed and built. The principle of visual localization and mapping algorithm is studied. According to the characteristics of UAV platform, the visual localization is designed and improved. Experimental results demonstrate that the UAV platform can realize the tasks of autonomous localization, navigation and mapping based on visual in unknown environments. © 2017, Shanghai Jiaotong University and Springer-Verlag Berlin Heidelberg.