Showing papers on "Guidance system published in 2019"

Deep Learning-Based Real-Time Multiple-Object Detection and Tracking from Aerial Imagery via a Flying Robot with GPU-Based Embedded Devices.

Abstract: In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-the-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one was designed using a Jetson TX or AGX Xavier, and the other was based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-the-art deep learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates, as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep learning-based association metric approach with simple online and real-time tracking (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.

Distributed Wildfire Surveillance with Autonomous Aircraft Using Deep Reinforcement Learning

Abstract: Teams of autonomous unmanned aircraft can be used to monitor wildfires, enabling firefighters to make informed decisions. However, controlling multiple autonomous fixed-wing aircraft to maximize fo...

Guidance and Control

Abstract: Guidance and Control focuses on space guidance models and behavior control techniques needed in space missions. Divided into eight parts with 30 chapters, the book contains the literature of authors who have conducted extensive research on factors affecting space missions. The concerns include ascent from Earth to an orbit requiring navigation as well as descent to Earth or the moon; the system aspects of inertial navigation; and developments in modern control theory and attitude control. The text looks at experiments on the launch of space missions and the different mathematical techniques used to measure the movement of a variable-mass vehicle. The selection also notes the processes and techniques involved in keeping satellites in compatible orbits; the influence of calculus of perturbations as applied to lunar mission analysis; and tracking of space vehicles through satellites and radar. The book also presents guidance systems for soft lunar landing and the longitudinal control of a lifting vehicle entering a planetary atmosphere. Other concerns include the application of sideband folding techniques to navigation satellite system; Damping an inertial navigation system; and application of multiple inertial system in navigation. The text ends by highlighting the use of gyroscopes in space navigation and infrared navigation sensors in space vehicles and how solar radiation affects pressure on satellite attitude control. The book is valuable for readers interested in studying the factors involved in space missions.

A COLREG-Compliant Ship Collision Avoidance Algorithm

Abstract: The compliance with the navigation rules plays a primary role in the development of routing algorithms to be applied in autonomous navigation. For such a reason this paper presents the mathematical formulations necessary to implement the Collision Regulations (COLREGs) within a previously developed ship path planning algorithm. The proposed approach is designed to be part of a decision support system for the bridge operators, in order to enhance traditional navigation; or, looking forward, to be part of the autonomous ship guidance system. Unlike other approaches that can be found in the scientific literature, the proposed work relies on the algebra of vectors, in order to describe the different scenarios as provided for in the COLREGs. The formulations to handle: head-on, crossing and overtaking, are formalized, described in detail and discussed. Eventually, some test cases are presented to show the effectiveness of the implementation of the proposed modeling into a Rapidly-exploring Random Tree (RRT*) algorithm. A simplified ship simulator is embedded in the algorithm to generate feasible solutions, taking into account the ship's manoeuvring capability.

A distributed dynamic route guidance approach based on short-term forecasts in cooperative infrastructure-vehicle systems

Abstract: This paper proposes and implements a simulation-based Distributed Dynamic Route Guidance System (DDRGS) by using the latest data collection and communication techniques in Cooperative Vehicle-Infrastructure Systems (CVIS). The framework and data processing procedure of DDRGS are designed by considering practical characteristics together with users' demands. Then, we formulate an integrated guidance model, which is based on Kalman filter short-term predicting information. A time-dimension factor is particularly introduced into the considered network with an innovative hierarchical scheme. Correspondingly, an improved Dijkstra algorithm for the guidance model is developed to find the optimal route. Further, we elaborately coordinate the DDRGS with the online map and other plug-in tools. The developed system shows that the approach proposed in this paper is available and effective for real-world applications.

Integrated guidance and control strategy for homing of unmanned underwater vehicles

Abstract: This paper presents a novel integrated guidance and control strategy for homing of unmanned underwater vehicles (UUVs) in 5-degree-of-freedom (DOF), where the vehicles are assumed to be underactuated at high speed and required to move towards the final docking path. During the initial homing stage, the guidance system is first designed by geometrical analysis method to generate a feasible reference trajectory. Then, in the backstepping framework, the proposed trajectory tracking controller can achieve all the tracking errors in the closed-loop system convergence to a small neighbourhood of zero. It means that the vehicle's dynamics are consistent with the reference trajectory derived in the previous step. To demonstrate the effectiveness of the proposed guidance and control strategy, the complete stability analysis used Lyapunov's method is given in the paper, and simulation results of all initial conditions are presented and discussed.

A Vision/Radar/INS Integrated Guidance Method for Shipboard Landing

Abstract: This paper presents a vision/radar/INS integrated guidance system for shipboard landing. The vision system on the aircraft tracks landmarks on the ship and outputs their coordinates in the image. The motion information of aircraft is obtained from airborne inertial navigation system (INS). Meanwhile, the datalink receives the relative position between the ship and aircraft from the shipboard radar and the ship motion information from shipboard sensors. The federated filter is utilized to fuse the vision, radar and inertial information, and the information from INS is chosen as the reference system in the federated filter. The estimated ship motion information is utilized to calculate the glide-down path. All the guidance information is regarded as the feedback information given to the flight control system to calculate control command. A designed on-vehicle experiment shows that the vision/radar/INS integrated landing guidance system achieves satisfied results.

An assisted telemanipulation approach: combining autonomous grasp planning with haptic cues

Abstract: This paper presents an assisted telemanipulation approach with integrated grasp planning. It also studies how the human teleoperation performance benefits from the incorporated visual and haptic cues while manipulating objects in cluttered environments. The developed system combines the widely used master-slave teleoperation with our previous model-free and learning-free grasping algorithm by means of a dynamic grasp re-ranking strategy and a semi-autonomous reach-to-grasptrajectory guidance. The proposed re-ranking metric helps in dynamically updating the stable grasps based on the current state of the slave device. The trajectory guidance system assists in maintaining smooth trajectory by controlling the haptic forces. A virtual pose controller has been integrated with the guidance scheme to automatically correct the end-effector orientation while reaching towards the grasp. Various experiments are conducted evaluating the proposed method using a six degrees of freedom (dof) haptic master and a seven dof slave robot. Results obtained with these tests along with the results gathered from the performed human-factor trials demonstrate the efficiency of our method in terms of objective metrics of task completion, and also subjective metrics of user experience.

UAV Flight and Landing Guidance System for Emergency Situations

Abstract: Unmanned aerial vehicles (UAVs) with high mobility can perform various roles such as delivering goods, collecting information, recording videos and more. However, there are many elements in the city that disturb the flight of the UAVs, such as various obstacles and urban canyons which can cause a multi-path effect of GPS signals, which degrades the accuracy of GPS-based localization. In order to empower the safety of the UAVs flying in urban areas, UAVs should be guided to a safe area even in a GPS-denied or network-disconnected environment. Also, UAVs must be able to avoid obstacles while landing in an urban area. For this purpose, we present the UAV detour system for operating UAV in an urban area. The UAV detour system includes a highly reliable laser guidance system to guide the UAVs to a point where they can land, and optical flow magnitude map to avoid obstacles for a safe landing.

A Robust Model-Predictive Guidance System for Autonomous Vehicles in Cluttered Environments

Abstract: This paper proposes a system for guidance of autonomous vehicles based on a generalized robust model-predictive control (R-MPC) technique. It offers two scenarios, in which R-MPC is used to provide optimized motion plans guaranteed to satisfy constraints and avoid obstacles in the presence of bounded uncertainty. The first scenario involves a military unmanned aerial vehicle flying over a target, while avoiding enemy defenses. The second scenario involves an assistive care robot safely navigating to waypoints throughout a cluttered home. In each case, obstacles are represented as a collection of linear inequality constraints that adapt to changes in the environment. Results show that when R-MPC is formulated using a series of positive-semidefinite relaxations on linear inequality constraints, safe optimum trajectories can be planned by solving a convex quadratic program. When formulated in terms of perturbations on feedback predictions, this solution is guaranteed to be robustly stable.

High-Gain Extended State Observer Based Adaptive Sliding Mode Path Following Control for An Underactuated Vessel Sailing in Restricted Waters

Abstract: This paper studied the path following problem for an underactuated vessel sailing in restricted waters with varying water depths. A novel high-gain extended state observer based adaptive sliding mode path following control scheme was proposed. The high-gain extended state observer based line-of-sight guidance law was designed according to vessel kinematics in the horizontal plane, which achieved accurate guidance in spite of time-varying sideslip angles. In the guidance system, a guidance angle was calculated to serve as a reference input for the yaw tracking control system. The sliding mode yaw tracking control system was designed, which can deal with model uncertainties and external disturbances. Since it is hard to obtain the exact model parameters in advance, an adaptive technique was adopted to estimate the unknown parameters, and an adaptive sliding mode control was designed to make the yaw tracking errors globally and asymptotically converge to zero in spite of unknown model parameters, model uncertainties, and external disturbances. Furthermore, the global uniformly asymptotically stability of the closed-loop system was proven based on the cascade system theory. Lastly, simulation experiments were conducted to validate the analysis results and to demonstrate the superiority of the proposed scheme.

Smart School Guidance and Vocational Guidance System Through the Internet of Things

Abstract: In the current era of scholar orientation in Morocco, social inequalities in school and professional pathways remain blatant. A referral process which consists of distributing students among the options, according to processes defined by the government and essentially based on academic performance. Vocational guidance in schools is a very necessary aspect that cannot be ignored throughout secondary education, where a bad orientation is often associated with failure or dropping out of school. This is indicated in the Moroccan Strategic Vision 2015-2030 which aims to improve the quality of the school and resume the system of educational and vocational guidance with a view to developing it and guarantee equal opportunities for students. In the context of vocational guidance, the article discuses and examines a smart school guidance system called "ETC guidance system", its role is to reduce failure orientation rate and create an environment conducive to the successful adaptation of school guidance according to students' cognitive trends, using Internet of things (IoT) and mobile devices. The system is easy to use and an innovative solution to guide students from third world countries, to choose the best professional career.

Life protection system for social disaster using convergence technology like camera sensor network and directional speaker system

Abstract: A human life protection system using a camera, a sensor network, and a directional speaker based on fusion technology for a social disaster response allows IoT sensor platform technology for a social disaster response, including a CCTV camera, a fusion sensor, an IoT sensor network (USN, WSN, 6LoWPAN, Wi-Fi, NB-IoT, LTE, and LoRa network), and an IoT gateway sensing a social disaster by using ICT technology, to be developed; provides a mobius server, an IDS integrated control system and an IDS local control system, sensor data monitoring, artificial intelligence-based disaster situation image analysis, situation awareness, or object tracking for an image of an image control system, sensor data monitoring, and a function of detecting an event by screaming sound in a dangerous area using a microphone sensor; provides big data analysis for each disaster type and a disaster response IDS-based human life protection system, evacuation guidance system, and disaster response system; provides disaster alert broadcasting and evacuation guidance technology using a directional speaker; and provides an evacuation guidance system using a sensor network and a directional speaker system capable of variable output, and a guidance application of a smartphone using the non-audible frequency.

Short-Range Reentry Guidance With Impact Angle and Impact Velocity Constraints for Hypersonic Gliding Reentry Vehicle

Abstract: In order to ensure the normal operation of the guidance system and achieve precise reentry strike, it is necessary to complete the reentry guidance in a very short range of several hundred kilometers. Furthermore, the process constraints, including the field of view and overload, and the terminal constraints, such as the impact velocity and impact angle, need to be met. To solve these problems, a guidance strategy for short-range gliding with maneuvering deceleration capability is proposed. First, the flight-path angle command is generated in real time using a reference trajectory in the longitudinal plane of the gliding flight phase to ensure the timely convergence of the trajectory and meet the handover conditions. Second, in the terminal attack phase, a weight coefficient of the angle control command is introduced and adjusted according to the vertical field-of-view deviation to force down the trajectory and maintain the field-of-view constraint. Finally, the deceleration angle of attack and the additional angle of attack are selected as the control variables, and the deceleration requirements of the gliding flight phase and the terminal attack phase are met using the predictor-corrector method. The numerical simulations verify that the proposed guidance strategy exhibit good guidance performance and robustness.

Effect of risk-predictive haptic guidance in one-pedal driving mode

Abstract: The research presented in this article focuses on the design of a driver support system for risk-predictive driving under a potentially hazardous situation for a pedestrian who crosses a road from the driver’s blind spots. Our aim is to develop a system that would cooperate with the driver in leading the normative speed calculated by the co-driver function. The design philosophy of haptic guidance is to communicate to the drivers the potentially hazardous situation through tactile cues from the active gas pedal and to assist drivers to in preparing for possible road surprises. We intended to combine the algorithm of the haptic feedback loop with the functionality of the one-pedal driving mode interface. Three design issues for the haptic guidance system can be distinguished: the design of a one-pedal driving mode based on a one-pedal operation; the modeling of risk-predictive driving behavior; and the haptic feedback algorithm with active gas pedal. We tested our system in human-in-the-loop experiments in a driving simulator to investigate (1) the effect of the one-pedal driving mode interface on the driver behavior and (2) the effect of haptic guidance support on the driver behavior. From the results of our experiments, we confirmed that haptic guidance can improve the risk-predictive driving performance for a slowdown task via the one-pedal driving mode.

Research on the Active Guidance Control System in High Speed Maglev Train

Abstract: The guidance system is one of the important subsystems of high-speed maglev train. The active guidance of high-speed maglev train is achieved by the attraction between the guide way and the electromagnets mounted on the side of the carriage. The working characteristics of the guidance system vary according to the different guide ways and weather conditions. In the straight line, the guiding current is very small. When suffering from the bend or big crosswind, the guiding current will be very large. Therefore, the model of the guidance system has greater uncertainty, and the guidance controller is more difficult to design. This paper presents a method to make the high-speed maglev train to obtain a stable guidance ability in different conditions. The mathematical model of the guidance system is established, and the robust guidance controller is designed by $H_{\infty } $ control theory. The simulation and experiment demonstrate that the high-speed maglev train using the designed guidance controller has relatively desirable performance and achieves stable guidance ability successfully.

Haptic Feedback Perception and Learning With Cable-Driven Guidance in Exosuit Teleoperation of a Simulated Drone

Abstract: Robotics teleoperation enables human operators to control the movements of distally located robots. The development of new wearable interfaces as alternatives to hand-held controllers has created new modalities of control, which are more intuitive to use. Nevertheless, such interfaces also require a period of adjustment before operators can carry out their tasks proficiently. In several fields of human-machine interaction, haptic guidance has proven to be an effective training tool for enhancing user performance. This paper presents the results of psychophysical and motor learning studies that were carried out with human participant to assess the effect of cable-driven haptic guidance for a task involving aerial robotic teleoperation. The guidance system was integrated into an exosuit, called the Flyjacket, that was developed to control drones with torso movements. Results for the just noticeable difference and from the Stevens Power Law suggest that the perception of force on the users’ torso scales linearly with the amplitude of the force exerted through the cables and the perceived force is close to the magnitude of the stimulus. Motor learning studies reveal that this form of haptic guidance improves user performance in training, but this improvement is not retained when participants are evaluated without guidance.

Field-of-View and Impact Angle Constrained Guidance Law for Missiles With Time-Varying Velocities

Abstract: A novel nonlinear non-switching guidance strategy is proposed for missiles with time-varying velocities intercepting stationary targets, considering impact angle, seeker's field-of-view, and input saturation constraints, simultaneously. A new nonlinear control oriented mathematical model is established, and the guidance design problem is converted to be the issue of tracking control of a nonlinear system with the partial state constraint. In the first step, a bounded virtual guidance law is designed based on hyperbolic tangent function. In the second step, the effect of the input saturation is compensated with a first-order filter. Integral barrier Lyapunov function based stability analysis shows that the tracking errors of the whole guidance system converge to zero uniformly, and the prescribed guidance constraints are not violated. Finally, the numerical simulations are performed to demonstrate the effectiveness of the proposed guidance law.

User performance evaluation and real-time guidance in cloud-based physical therapy monitoring and guidance system

Abstract: The effectiveness of traditional physical therapy may be limited by the sparsity of time a patient can spend with the physical therapist (PT) and the inherent difficulty of self-training given the paper/figure/video instructions provided to the patient with no way to monitor and ensure compliance with the instructions. In this paper, we propose a cloud-based physical therapy monitoring and guidance system. It is able to record the actions of the PT as he/she demonstrates a task to the patient in an offline session, and render the PT as an avatar. The patient can later train himself by following the PT avatar and getting real-time guidance on his/her device. Since the PT and user (patient) motion sequences may be misaligned due to human reaction and network delays, we propose a Gesture-Based Dynamic Time Warping algorithm that can segment the user motion sequence into gestures, and align and evaluate the gesture sub-sequences, all in real time. We develop an evaluation model to quantify user performance based on different criteria provided by the PT for a task, trained with offline subjective test data consisting of user performance and physical therapist scores. Moreover, we design three types of guidance which can be provided after each gesture based on user score, and conduct subjective tests to validate their effectiveness. Experiments with multiple subjects show that the proposed system can effectively train patients, give accurate evaluation scores, and provide real-time guidance which helps the patients learn the tasks and reach the satisfactory score with less time.

Adaptive Guidance with Reinforcement Meta-Learning

Abstract: This paper proposes a novel adaptive guidance system developed using reinforcement meta-learning with a recurrent policy and value function approximator. The use of recurrent network layers allows the deployed policy to adapt real time to environmental forces acting on the agent. We compare the performance of the DR/DV guidance law, an RL agent with a non-recurrent policy, and an RL agent with a recurrent policy in four difficult tasks with unknown but highly variable dynamics. These tasks include a safe Mars landing with random engine failure and a landing on an asteroid with unknown environmental dynamics. We also demonstrate the ability of a recurrent policy to navigate using only Doppler radar altimeter returns, thus integrating guidance and navigation.

Enhanced predictor–corrector Mars entry guidance approach with atmospheric uncertainties

Abstract: Due to the long-range data communication and complex Mars environment, the Mars lander needs to promote the ability to autonomously adapt uncertain situations ensuring high precision landing in future Mars missions. Based on the analysis of multiple disturbances, this study demonstrates an enhanced predictor–corrector guidance method to deal with the effect of atmospheric uncertainties during the entry phase of the Mars landing. In the proposed method, the predictor–corrector guidance algorithm is designed to autonomously drive the Mars lander to the parachute deployment. Meanwhile, the disturbance observer is designed to onboard estimate the effect of fiercely varying atmospheric uncertainties resulting from rapidly height decreasing. Then, with the estimation of atmospheric uncertainties compensated in the feed-forward channel, the composite guidance method is put forward such that both anti-disturbance and autonomous performance of the Mars lander guidance system are improved. Convergence of the proposed composite method is analysed. Simulations for a Mars lander entry guidance system demonstrates that the proposed method outperforms the baseline method in consideration of the atmospheric uncertainties.

Three-Dimensional Fast Fixed-time Convergence Guidance Law With Impact Angle Constraint

Abstract: In this paper, a three-dimensional (3D) impact-angle-control guidance law is proposed based on the approaches of nonsingular terminal sliding mode control and fixed-time convergence theory to intercept a maneuvering target. The guidance law is derived based on the coupled 3D engagement dynamics. To intercept the target with an expected impact angle, the nonsingular terminal sliding mode control is designed to ensure that the line-of-sight (LOS) angles and rates rapidly reach the desired values. Furthermore, the fixed-time convergence algorithm is proposed to guarantee that the LOS angles and rates are convergent in fixed time. The upper bound of the settling time can be obtained by presetting the parameters of the proposed guidance law, and it is independent of the initial conditions. The stability of the guidance system is proven via Lyapunov stability theory. The simulation results are presented to validate the efficiency and superiority of the proposed guidance law.