Autonomous UAV Development and Evaluationwith MATLAB and Simulink Julia AntoniouAndrew Grabowski0
Autonomous UAV Development and EvaluationMATLAB Integrated workflows enabledby MATLAB and Simulink Tools to design UAV systemsand autonomous applications Select appropriate methods foryour UAV development tasks Evaluating systems throughclosed-loop simulations withsensor modelsSimulink 1
Autonomous UAV Development and EvaluationMATLAB Integrated workflows enabledby MATLAB and Simulink Tools to design UAV systemsand autonomous applications Select appropriate methods foryour UAV development tasks Evaluating systems throughclosed-loop simulations withsensor modelsSimulink 2
Increase in autonomous UAV usageMapping &SurveyingInspections &MonitoringDelivery &TransportSecurity &Defense3
Challenges in developing autonomous UAV systems & applicationsComplexity of advancedautonomous algorithmsNeed of end-to-end workflowsEnsuring system quality andreducing flight risk4
Solutions for developing autonomous UAV systems & applicationsRobust tools and features fordesigning and testing UAV systemsand algorithmsIntegrated development environmentthat covers development from ideasto productionExtensive verification and validationtools to evaluate design qualitythrough virtual testing5
Integrated workflows for developing UAV applicationsMATLAB Simulink System Architecture6
Integrated workflows for developing UAV applicationsMATLAB Simulink System ArchitectureModel UAV7
Integrated workflows for developing UAV applicationsMATLAB Simulink System ArchitectureModel UAVDesign AlgorithmsPerceptionControlPlanning &Decision8
Integrated workflows for developing UAV applicationsMATLAB Simulink Verification & ValidationSystem ArchitectureModel UAVDesign AlgorithmsPerceptionControlPlanning &DecisionDO-1789
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDesign AlgorithmsPerceptionControlPlanning &DecisionDO-17810
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlPlanning &DecisionImplementPX4 NVIDIA Jetson DO-17811
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectDO-178ConnectUAVGround Control Station12
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlDO-178ImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectAnalyze DataConnectUAVGround Control Station13
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAV System Composer fordesigning and analyzingsystem and softwareDesign AlgorithmsarchitecturePerceptionGazeboUnreal EngineDeploy to HardwareImplementPlanning &DecisionControlSimulink O-178traceability CuboidPX4 NVIDIA Jetson ConnectConnectUAVGround Control StationLink14
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlDO-178ImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectAnalyze DataConnectUAVGround Control Station15
UAV Plant Modeling: Selecting the appropriate fidelityHigh-FidelityBuilding UAVSimscape Multibody, Aerospace Blockset, UAV ToolboxApproximateProgramming UAV16
UAV Plant Modeling: Selecting the appropriate fidelityHigh-FidelityBuilding UAVApproximateProgramming UAVLinkSimscape Multibody, Aerospace Blockset, UAV Toolbox17
UAV Plant Modeling: Selecting the appropriate fidelityHigh-FidelityBuilding UAVApproximateProgramming UAVLinkSimscape Multibody, Aerospace Blockset, UAV ToolboxLink18
UAV Plant Modeling: Selecting the appropriate fidelityHigh-FidelityBuilding UAVApproximateProgramming UAVLinkSimscape Multibody, Aerospace Blockset, UAV ToolboxLinkLink19
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlDO-178ImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectAnalyze DataConnectUAVGround Control Station20
Autonomous UAV Algorithm DevelopmentDesign AlgorithmsPerceptionControlPlanning &DecisionMap DataEndpointStartpointPlanned Path21
Autonomous UAV algorithm design with robust capabilitiesPlanning uationalAwarenessLinkLinkLinkSensor Fusion and Tracking Toolbox, Lidar Toolbox, Navigation Toolbox, Computer Vision Toolbox, Deep Learning ToolboxLink22
Autonomous UAV algorithm design with robust capabilitiesPlanning &DecisionPerceptionControlLinkDefine UAV missions with waypointand trajectory-following algorithmsUAV Toolbox, Navigation ToolboxLinkUAV motion planning withadvanced path planners23
Autonomous UAV algorithm design with robust capabilitiesPerceptionPlanning &DecisionControlLinkTrajectory tracking controller with nonlinearmodel predictive control (MPC)Model Predictive Control Toolbox, Reinforcement Learning ToolboxLinkTrain policies for trajectory generationusing reinforcement learning algorithms24
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlDO-178ImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectAnalyze DataConnectUAVGround Control Station25
Tracking and automating verification and validation activitiesRequirements TraceabilityTest Management & AutomationLinkSimulink Requirements, Simulink Test, Simulink Coverage, Simulink CheckLinkEvaluate CompletenessLink26
Example: Automating UAV testing with requirements linkingAutomating test execution and evaluationRequirements linking for traceabilityUAV Toolbox, Simulink Requirements, Simulink TestLink27
Integrated workflows for developing UAV applicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlDO-178ImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectAnalyze DataConnectUAVGround Control Station29
Integrated simulations with sensor modelsUnreal Engine PhotorealisticCuboidPerformanceRapidly author scenarios andgenerate sensor dataUAV ToolboxRealistic graphics to test autonomousalgorithms in closed-loop simulationsLinkLink30
Integrated simulations with sensor modelsUnreal Engine PhotorealisticCuboidPerformanceRapidly author scenarios andgenerate sensor dataUAV ToolboxRealistic graphics to test autonomousalgorithms in closed-loop simulationsLinkLink31
Integrated simulations with sensor modelsUnreal Engine PhotorealisticCuboidPerformanceRapidly author scenarios andgenerate sensor dataUAV ToolboxRealistic graphics to test autonomousalgorithms in closed-loop simulationsLinkLink32
Example: Build 3D map using simulation Lidar point cloud dataExecute simulationObtain sensor dataUAV Toolbox, Lidar ToolboxExtract and match featuresRegister and align point cloudDetect loop-closuresCreate pose graphOptimize poses33
Create 3D scenes for UAV simulationsLinkLinkDesign 3D scenes for simulating and testing autonomous algorithmsRoadRunner, RoadRunner Asset Library, UAV Toolbox Interface for Unreal Engine Projects34
Automatic code generation for hardware implementationMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureDeploy flight controls toautopilot hardwareModel UAVCuboidGazeboLinkUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionPlanning &DecisionControlCPUImplementPX4 GPUAnalyze DataDO-178FPGAROSConnectConnectDeploy autonomousalgorithms to onboardcomputersUAVUAV Toolbox, Simulink Coder, Embedded Coder, GPU CoderNVIDIA Jetson Link Control StationGround35
Connecting to UAV hardware through MAVLink protocolSimulink MATLAB Simulate with Sensor ModelsCompute BoardSystem ArchitectureMAVLinkMAVLinkVerification & ValidationRemote UAVModel UAVMAVLinkAutopilotHost MachineCuboidUAVMAVLink ConnectivityDesign AlgorithmsPerceptionControlDO-178Unreal EngineMessage BlocksDeployto HardwareImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectAnalyze DataConnectLinkUAV ToolboxGazeboUAVGround Control Station36
Post-flight data analysisMATLAB Simulink Simulate with Sensor ModelsFlight Log AnalysisPayload Data AnalysisVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlDO-178ImplementPlanning &DecisionLinkPX4 NVIDIA Jetson ConnectAnalyze DataConnectLinkUAVUAV Toolbox, Computer Vision Toolbox, Deep Learning ToolboxLinkGround Control Station37
Integrated Workflows for Developing UAV ApplicationsMATLAB Simulink Simulate with Sensor ModelsVerification & ValidationSystem ArchitectureModel UAVCuboidGazeboUnreal EngineDeploy to HardwareDesign AlgorithmsPerceptionControlDO-178ImplementPlanning &DecisionPX4 NVIDIA Jetson ConnectAnalyze DataConnectUAVGround Control Station39
Key TakeawaysIntegrated development workflowsfrom prototyping to productizationwith MATLAB and SimulinkCall To Action: Download presentation fileand investigate linkedexamples and pages Contact us for to learnmore details or for trialsRobust tools/features forautonomous UAV design andsimulations with sensor modelsQuality through verification & validationtools for traceability, test completeness,and test management/automation40
Thank you 2021 The MathWorks, Inc. MATLAB and Simulink are registered trademarks of The MathWorks, Inc. See mathworks.com/trademarksfor a list of additional trademarks. Other product or brand names may be trademarks or registered trademarks of their respective holders.41
Q&A42
Challenges in developing autonomous UAV systems & applications Complexity of advanced autonomous algorithms Need of end-to-end workflows Ensuring system quality and reducing flight risk Which of these challenges have you encountered? Enter in chat if you have others. Also enter in chat if you have tips on how you have resolved these challenges.
UAV Task-Force Final Report Chapter 1 3 11 May 2004 1 INTRODUCTION 1.1 BACKGROUND The Joint JAA/EUROCONTROL initiative on UAVs (hereinafter addressed by “UAV Task-Force” or “UAV T-F”) was established in September 2002 on the basis of a joint decision of the JAA and EUROCONTROL governing bodies. This decision was taken in reaction to the growing European UAV Industry and their .
Page 2 Autonomous Systems Working Group Charter n Autonomous systems are here today.How do we envision autonomous systems of the future? n Our purpose is to explore the 'what ifs' of future autonomous systems'. - 10 years from now what are the emerging applications / autonomous platform of interest? - What are common needs/requirements across different autonomous
1.3 Chapter Outline 1 2 3 2 LITERATURE REVIEW 4 2.1 Recent UAV Development 2.2 Design of Fuselage and Empennage of UAV 2.3 Ways of Deployment of UAV 2.4 Breakthrough in Aerospace Composites Manufacturing 2.5 Low Cost Composites Structure Manufacturing Techniques 2.6 Low Cost Expandable UAV 4 7 9 13 15 19
Unmanned aerial vehicle( UAV), Virtual simulation, Visualization ABSTRACT: With. the. advent of the 5G era of digital smart city, "UAV Application" is booming, and there is more and more demand for UAV remote sensing technology. How to cultivate high-tech application talents of UAV has become the primary problem to be solved in
(Figure 2), while the UAV (or drone/UAS) used was senseFly's eBee Plus UAV. This UAV had its built-in RTK/PPK function enabled (Figure 2) and was equipped with a senseFly S.O.D.A RGB camera. Figure 2: senseFly's eBee Plus UAV (left) with Trimble's SX10 hand controller (center) and SX10 scanning total station with carry case (right).
Reinforcement learning (RL) could help overcome this issue by allowing a UAV or a team of UAVs to learn and navigate through the changing environment without the need for modeling [8]. RL algorithms have already been extensively researched in UAV applications, as in many other elds of robotics [9], [10]. Several papers focus on applying RL .
the autonomous navigation of these systems. The global positioning system (GPS) is used for external autonomous navigation [1]. Because GPS signals are typically absent or weak indoors, autonomous navigation is difficult [2]. There are various approaches for independent indoor navigation which have been proposed in recent years.
Samy T. (Purdue) Rough Paths 1 Aarhus 2016 12 / 16. Study of equations driven by fBm Basicproperties: 1 Momentsofthesolution 2 Continuityw.r.tinitialcondition,noise Moreadvancednaturalproblems: 1 Densityestimates, Hu-Nualart Lotsofpeople 2 Numericalschemes, Neuenkirch-T,Friz-Riedel 3 Invariantmeasures,ergodicity, Hairer-Pillai,Deya-Panloup-T 4 Statisticalestimation(H,coeff. V j .