- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add matlab/matlab-agentic-toolkit --skill matlab-use-ncap-protocol -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add matlab/matlab-agentic-toolkit --skill matlab-use-ncap-protocol -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add matlab/matlab-agentic-toolkit --skill matlab-use-ncap-protocol -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add matlab/matlab-agentic-toolkit --skill matlab-use-ncap-protocol -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/matlab/matlab-agentic-toolkit/tree/HEAD/skills-catalog/automotive/matlab-use-ncap-protocol来自发布者
Create Euro NCAP seed scenarios, generate variants, translate between simulators, plot descriptors, and compute scores using the ADT Euro NCAP support package APIs.
variationProperties for non-NCAP scenariosUser wants Euro NCAP scenarios?
│
├─ Protocol year 2023 (or unspecified)?
│ └─ Use standalone: ncapScenario("SA AEB CCFtap")
│ - Test names use prefix: "SA AEB", "SA LSS", "VRU AEB", "VRU LSS"
│ - Supports ShowProgress name-value
│ - Returns ScenarioDescriptor
│
└─ Protocol year 2026?
└─ Use euroAssessment path:
1. ea = euroAssessment(2026)
2. configureVUT(ea, ...) — if custom VUT needed
3. descriptor = ncapScenario(ea, "CA FC CCFtap")
- Test names use prefix: "CA FC"
- Does NOT support ShowProgress
- Required for scoring/reporting workflow
Use when you need just the seed scenario (1 descriptor), not all variants.
% 2023 standalone — single seed
descriptor = ncapScenario("SA AEB CCFtap");
% 2026 via euroAssessment — single seed
ea = euroAssessment(2026);
descriptor = ncapScenario(ea, "CA FC CCFtap");
AllScenarios=true generates the seed AND all protocol-defined variants. Do NOT use it when only the seed is requested.
Output arguments: The two-output form [descriptors, scenarioInfo] = ncapScenario(...) requires AllScenarios=true. Without it, only one output is allowed — requesting two outputs errors with "Too many output arguments".
Use when the user wants all test variants for a given scenario.
% 2023 — all variants with progress
[descriptors, scenarioInfo] = ncapScenario("SA AEB CCCscp", AllScenarios=true);
% 2026 — all variants
ea = euroAssessment(2026);
[descriptors, scenarioInfo] = ncapScenario(ea, "CA FC CCCscp", AllScenarios=true);
The ShowProgress name-value controls built-in progress display during generation.
% Show command-line progress (default behavior)
descriptor = ncapScenario("SA AEB CCRs", ShowProgress="CommandLine");
% Suppress progress
descriptor = ncapScenario("SA AEB CCRs", ShowProgress="No");
Important: ShowProgress is only supported on the standalone ncapScenario(testName) call. It is NOT supported when using the euroAssessment overload ncapScenario(ea, testName).
When the user asks to "show progress" or "display progress", use ShowProgress="CommandLine" (or omit it since it's the default). Do NOT set ShowProgress="No" and then implement manual fprintf progress.
Use getScenario to translate a descriptor to either simulator. Never export to OpenSCENARIO and re-import as a translation method.
% Descriptor → drivingScenario
ds = getScenario(descriptor, Simulator="DrivingScenario");
% Descriptor → RoadRunner (requires active RoadRunner instance)
rrApp = roadrunner("C:/path/to/project");
rrScen = getScenario(descriptor, Simulator="RoadRunner", SimulatorInstance=rrApp);
Key rules:
getScenario requires Name-Value syntax. Simulator must be specified as a Name-Value pair, not a positional argument.Simulator="DrivingScenario": accepts an array of descriptors and returns an array of drivingScenario objects.Simulator="RoadRunner": accepts only a single descriptor per call — returns one Simulink.ScenarioSimulation object. Passing an array errors with "Too many input arguments". Loop over descriptors individually for batch RoadRunner translation.sdp = plot(descriptors);
configure(sdp, Title="My Scenarios", GridSize=[3 4], ...
SubPlotTitles=["Variant 1", "Variant 2", "Variant 3"]);
ScenarioDescriptorPlot supports a maximum of 20 subplots per figure via GridSize. For larger arrays, split across multiple calls:
% Plot first 20
sdp1 = plot(descriptors(1:20));
configure(sdp1, Title="Variants 1-20", GridSize=[4 5]);
% Plot remaining
sdp2 = plot(descriptors(21:end));
configure(sdp2, Title="Variants 21-30", GridSize=[2 5]);
sdp = plot(descriptor);
play(sdp); % Animate the scenario
seek(sdp, 2.5); % Jump to t=2.5s
close(sdp); % Close figure
% 1. Create assessment object
ea = euroAssessment(2026);
% 2. Configure VUT (optional)
configureVUT(ea, StabilizationTime=2, AssetPath="Vehicles/SK_SUV.fbx");
% 3. Generate all variants
[descriptors, scenarioInfo] = ncapScenario(ea, "CA FC CCFtap", AllScenarios=true);
% 4. Create assessment table and populate results
% Column names are test-dependent — inspect with at.Properties.VariableNames
% Common columns: ImpactVelocity (CCFtap, CCCscp) or RelativeImpactVelocity (CCRs, CCRm, CCRb)
at = assessmentTable(ea, "CA FC CCFtap");
at.ImpactVelocity = zeros(height(at), 1); % Replace with actual sim results
% 5. Compute score (returns struct, not scalar)
[score, updatedTable] = ncapScore(ea, "CA FC CCFtap", at);
fprintf("Total score: %.2f / %.2f\n", score.AggregateScore.Total, score.AvailableScore.Total);
% 6. Generate report figure
fig = ncapReport(ea, "CA FC CCFtap");
% 7. Export report to file
exportReport(ea, "CA FC CCFtap", "ncap_report.pdf");
Use table2scenario to create a ScenarioDescriptor from user-defined tabular data. This is the programmatic entry point when you have scenario parameters in table form rather than using the predefined NCAP test definitions.
% Scene: straight road, 100m
sceneSpec = table(1, {'Straight'}, 100, 0, NaN, ...
VariableNames=["RoadElementID", "RoadElementType", "Length_Radius", ...
"DeltaHeading", "ParentIntersectionID"]);
% Actor: one car (Ego) on road 1, lane 1
actorSpec = table(1, 1, 1, {'Car'}, {'Ego'}, ...
{'4.7, 1.8, 1.4, 0.5, 0.9, 2.8'}, {'Along'}, {'10%, 50%'}, ...
VariableNames=["ActorID", "RoadID", "LaneID", "ActorType", ...
"ActorName", "Dimension", "Heading", "RelativePosition"]);
% Event: fixed velocity start at 15 m/s
eventSpec = table(1, 1, {'FixedVelocityStart'}, 15, NaN, NaN, ...
VariableNames=["EventID", "ActorID", "EventType", "Speed", ...
"Distance", "EventTrigger"]);
descriptor = table2scenario(sceneSpec, actorSpec, eventSpec);
Key rules:
sceneSpec columns: RoadElementID, RoadElementType, Length_Radius, DeltaHeading, ParentIntersectionIDactorSpec columns: ActorID, RoadID, LaneID, ActorType, ActorName, Dimension, Heading, RelativePositioneventSpec columns: EventID, ActorID, EventType, Speed, Distance, EventTriggerScenarioDescriptor — same type as ncapScenario outputgetScenario, plot, generateVariants% Configure export options
opts = openScenarioXMLExportOptions(RelocateVehicleOrigin=true);
% Export from RoadRunner
exportScenario(rrApp, "output.xosc", "OpenSCENARIO XML", opts);
See references/export-options.md for full export configuration details.
Critical: Euro NCAP test names must be specified in full. Short names like "CCFtap" or "CCCscp" are NOT valid.
The short code (e.g., CCFtap, CCCscp, CCRs) is always the LAST part of the full name.
See references/ncap-test-names.md for the complete lookup table of all valid test names.
euroAssessment(2026) for any 2026-protocol workflow (scoring, reporting, configureVUT)ncapScenario(testName) for simple 2023 generation without scoringgetScenario for ALL simulator translations — never export+reimportexportReport (R2026a) for file export — do not write custom report export codeexportScenario (roadrunner method) for OpenSCENARIO export from RoadRunnerRelocateVehicleOrigin=true in export options when rear axle reference is neededCopyright 2026 The MathWorks, Inc.
>
---name: matlab-use-ncap-protocoldescription: >---# skills-catalog/automotive/matlab-use-ncap-protocol/SKILL.md常见问题
从发布者处下载 skills-catalog/automotive/matlab-use-ncap-protocol/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/matlab/matlab-agentic-toolkit。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。
| Invalid value error |
Use: "None", "GlobalWaypoint", "DynamicWaypoint", or "RuntimeActorsCrop" |
plot(descriptors) with GridSize > [4 5] | Max 20 subplots per figure | Split array into chunks of ≤20 |
fprintf("%.2f", score) after ncapScore | score is a struct, not scalar | Access score.AggregateScore.Total for the numeric value |
exportReport(ea, name, "report.html") | HTML not supported | Use .pdf, .png, or .jpg extension |
at.ImpactVelocity = ... for CCRs/CCRm/CCRb tests | Column is RelativeImpactVelocity, not ImpactVelocity | Check at.Properties.VariableNames after assessmentTable — use the actual column name |
getScenario(descriptors, Simulator="RoadRunner", ...) with array | RoadRunner only accepts one descriptor at a time | Loop: for i=1:numel(descriptors), getScenario(descriptors(i), ...); end |