锐客网

  1. 首页 > it技术 > >

MATLAB|【智能驾驶】基于合成雷达的传感器融合的智能驾驶MATLAB仿真

matlab智能驾驶

% Define an empty scenario. scenario = drivingScenario; scenario.SampleTime = 0.01; %% % Add a stretch of 500 meters of typical highway road with two lanes. The % road is defined using a set of points, where each point defines the center of % the road in 3-D space. roadCenters = [0 0; 50 0; 100 0; 250 20; 500 40]; road(scenario, roadCenters, 'lanes',lanespec(2)); %% % Create the ego vehicle and three cars around it: one that overtakes the % ego vehicle and passes it on the left, one that drives right in front of % the ego vehicle and one that drives right behind the ego vehicle. All the % cars follow the trajectory defined by the road waypoints by using the % |trajectory| driving policy. The passing car will start on the right % lane, move to the left lane to pass, and return to the right lane.% Create the ego vehicle that travels at 25 m/s along the road.Place the % vehicle on the right lane by subtracting off half a lane width (1.8 m) % from the centerline of the road. egoCar = vehicle(scenario, 'ClassID', 1); trajectory(egoCar, roadCenters(2:end,:) - [0 1.8], 25); % On right lane% Add a car in front of the ego vehicle leadCar = vehicle(scenario, 'ClassID', 1); trajectory(leadCar, [70 0; roadCenters(3:end,:)] - [0 1.8], 25); % On right lane% Add a car that travels at 35 m/s along the road and passes the ego vehicle passingCar = vehicle(scenario, 'ClassID', 1); waypoints = [0 -1.8; 50 1.8; 100 1.8; 250 21.8; 400 32.2; 500 38.2]; trajectory(passingCar, waypoints, 35); % Add a car behind the ego vehicle chaseCar = vehicle(scenario, 'ClassID', 1); trajectory(chaseCar, [25 0; roadCenters(2:end,:)] - [0 1.8], 25); % On right lane%% Define Radar Sensors % Simulate an ego vehicle that has 6 radar sensors and % The ego vehicle is equipped with a % long-range radar sensor. Each side of the vehicle has two short-range radar % sensors, each covering 90 degrees. One sensor on each side covers from % the middle of the vehicle to the back. The other sensor on each side % covers from the middle of the vehicle forward. The figure in the next % section shows the coverage.sensors = cell(6,1); % Front-facing long-range radar sensor at the center of the front bumper of the car. sensors{1} = radarDetectionGenerator('SensorIndex', 1, 'Height', 0.2, 'MaxRange', 174, ... 'SensorLocation', [egoCar.Wheelbase + egoCar.FrontOverhang, 0], 'FieldOfView', [20, 5]); % Rear-facing long-range radar sensor at the center of the rear bumper of the car. sensors{2} = radarDetectionGenerator('SensorIndex', 2, 'Height', 0.2, 'Yaw', 180, ... 'SensorLocation', [-egoCar.RearOverhang, 0], 'MaxRange', 174, 'FieldOfView', [20, 5]); % Rear-left-facing short-range radar sensor at the left rear wheel well of the car. sensors{3} = radarDetectionGenerator('SensorIndex', 3, 'Height', 0.2, 'Yaw', 120, ... 'SensorLocation', [0, egoCar.Width/2], 'MaxRange', 30, 'ReferenceRange', 50, ... 'FieldOfView', [90, 5], 'AzimuthResolution', 10, 'RangeResolution', 1.25); % Rear-right-facing short-range radar sensor at the right rear wheel well of the car. sensors{4} = radarDetectionGenerator('SensorIndex', 4, 'Height', 0.2, 'Yaw', -120, ... 'SensorLocation', [0, -egoCar.Width/2], 'MaxRange', 30, 'ReferenceRange', 50, ... 'FieldOfView', [90, 5], 'AzimuthResolution', 10, 'RangeResolution', 1.25); % Front-left-facing short-range radar sensor at the left front wheel well of the car. sensors{5} = radarDetectionGenerator('SensorIndex', 5, 'Height', 0.2, 'Yaw', 60, ... 'SensorLocation', [egoCar.Wheelbase, egoCar.Width/2], 'MaxRange', 30, ... 'ReferenceRange', 50, 'FieldOfView', [90, 5], 'AzimuthResolution', 10, ... 'RangeResolution', 1.25); % Front-right-facing short-range radar sensor at the right front wheel well of the car. sensors{6} = radarDetectionGenerator('SensorIndex', 6, 'Height', 0.2, 'Yaw', -60, ... 'SensorLocation', [egoCar.Wheelbase, -egoCar.Width/2], 'MaxRange', 30, ... 'ReferenceRange', 50, 'FieldOfView', [90, 5], 'AzimuthResolution', 10, ... 'RangeResolution', 1.25); %% Create a Tracker % Create a || to track % the vehicles that are close to the ego vehicle. The tracker uses the % |initSimDemoFilter| supporting function to initialize a constant velocity % linear Kalman filter that works with position and velocity. % % Tracking is done in 2-D. Although the sensors return measurements in 3-D, % the motion itself is confined to the horizontal plane, so there is no % need to track the height.%% TODO* %Change the Tracker Parameters and explain the reasoning behind selecting %the final values. You can find more about parameters here: https://www.mathworks.com/help/driving/ref/multiobjecttracker-system-object.htmltracker = multiObjectTracker('FilterInitializationFcn', @initSimDemoFilter, ... 'AssignmentThreshold', 30, 'ConfirmationParameters', [4 5], 'NumCoastingUpdates', 5); positionSelector = [1 0 0 0; 0 0 1 0]; % Position selector velocitySelector = [0 1 0 0; 0 0 0 1]; % Velocity selector% Create the display and return a handle to the bird's-eye plot BEP = createDemoDisplay(egoCar, sensors); %% Simulate the Scenario % The following loop moves the vehicles, calls the sensor simulation, and % performs the tracking. % % Note that the scenario generation and sensor simulation can have % different time steps. Specifying different time steps for the scenario % and the sensors enables you to decouple the scenario simulation from the % sensor simulation. This is useful for modeling actor motion with high % accuracy independently from the sensor's measurement rate. % % Another example is when the sensors have different update rates. Suppose % one sensor provides updates every 20 milliseconds and another sensor % provides updates every 50 milliseconds. You can specify the scenario with % an update rate of 10 milliseconds and the sensors will provide their % updates at the correct time. % % In this example, the scenario generation has a time step of 0.01 second, % while the sensors detect every 0.1 second. The sensors return a logical % flag, |isValidTime|, that is true if the sensors generated detections. % This flag is used to call the tracker only when there are detections. % % Another important note is that the sensors can simulate multiple % detections per target, in particular when the targets are very close to % the radar sensors. Because the tracker assumes a single detection per % target from each sensor, you must cluster the detections before the % tracker processes them. This is done by the function |clusterDetections|. % See the 'Supporting Functions' section.toSnap = true; while advance(scenario) && ishghandle(BEP.Parent) % Get the scenario time time = scenario.SimulationTime; % Get the position of the other vehicle in ego vehicle coordinates ta = targetPoses(egoCar); % Simulate the sensors detections = {}; isValidTime = false(1,6); for i = 1:6 [sensorDets,numValidDets,isValidTime(i)] = sensors{i}(ta, time); if numValidDets detections = [detections; sensorDets]; %#ok end end% Update the tracker if there are new detections if any(isValidTime) vehicleLength = sensors{1}.ActorProfiles.Length; detectionClusters = clusterDetections(detections, vehicleLength); confirmedTracks = updateTracks(tracker, detectionClusters, time); % Update bird's-eye plot updateBEP(BEP, egoCar, detections, confirmedTracks, positionSelector, velocitySelector); end% Snap a figure for the document when the car passes the ego vehicle if ta(1).Position(1) > 0 && toSnap toSnap = false; snapnow end end

MATLAB|【智能驾驶】基于合成雷达的传感器融合的智能驾驶MATLAB仿真
文章图片

【MATLAB|【智能驾驶】基于合成雷达的传感器融合的智能驾驶MATLAB仿真】 D203

    推荐阅读


    上一篇：一个关于wait/notify与锁关系的探究

    下一篇：MATLAB|模版匹配定位跟踪