본문으로 건너뛰기
cccskills
무료GitHub에 공개

carla-vehicle-authoring

Create, migrate, improve, or debug detailed vehicle assets for CARLA using Blender and Unreal, including reference-based geometry, materials, wheels, physics, lights, and runtime validation. Use for vehicle asset authoring rather than ordinary traffic spawning or map decoration.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구Blender
설치 방법 보기

포함된 파일(6)

  • SKILL.md3.8 KB
  • agents/openai.yaml254 B
  • references/carla-integration.md5.2 KB
  • references/validation-delivery.md4.3 KB
  • references/visual-authoring.md3.9 KB
  • scripts/env.sh245 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

CARLA vehicle authoring

Produce an editable, reproducible vehicle that looks convincing in CARLA cameras and behaves correctly through the CARLA API. Scale work to the request: a tire correction does not require rebuilding the entire vehicle.

Establish the target

Source scripts/env.sh using its absolute path to load the library's recorded configuration while preserving explicit environment overrides. Use CARLA_UE58_ROOT and CARLA_UNREAL_ENGINE_PATH when set; discover missing paths below. All supporting paths are relative to this SKILL.md.

Inspect repository instructions, code/content branches, existing vehicle tooling, and running editor/server sessions. Locate the actual repositories; do not assume the last session's paths, ports, or running processes. Preserve unrelated servers and unsaved Blender work. Use a dedicated server for tests that change weather, synchronous mode, or world state.

Determine the vehicle's year, trim, wheel option, interior, intended camera distances, and traffic-density needs from the request and available context. State consequential assumptions. For fidelity work, retrieve and visually inspect real references before modeling: manufacturer dimensions plus front, rear, side, wheel, lamp, and cabin photographs. Distinguish nominal body width from mirror-inclusive width. Record URLs, provenance, licenses, and source hashes; inspection references are not automatically licensed textures. Describe licensed base-model improvements honestly.

Choose the relevant workflow

For the proven reference implementation, locate Util/VehicleAuthoring/TeslaModel3/ in the CARLA code repo. Read its README and the relevant scripts before adapting them. It is a vehicle-specific reference implementation, not a generic importer: model names, geometry selections, physical values, paths, and test assumptions need adaptation. If unavailable, use the guidance here and the target branch's actual APIs.

Work in reviewable increments

Keep an unposed export master separate from posed inspection copies. Preserve reproducible source-generation/export steps, import settings, and asset identities. Establish correct scale, silhouette, wheel anchors, and basic runtime behavior before investing in fine detail. Review each meaningful visual increment in Blender and CARLA under matched camera and lighting conditions.

Debug the full chain: source geometry → exported geometry/material slots → saved Unreal assets → runtime components/state → sensor image. Do not assume a successful import, an API state round-trip, or a plausible render proves the next layer works. Reopen saved assets in a fresh process when persistence matters.

End with the editable source, integrated assets, reproducible tooling, provenance, and evidence appropriate to the requested scope. State remaining fidelity, dynamics, and performance limits. Commit/push only within the user's authorization; asset creation alone does not request publication.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Adds a new ROS 2 message type to CARLA's native ROS 2 interface — the hand-written POD struct under LibCarla/source/carla/ros2/types/msg, its Fast-CDR serialize/deserialize pair, the RIHS01 type hash computed in Docker, the CdrTopicInfo registration and the type-hash test. Use when the user asks to "add a ROS message type", "support sensor_msgs/X in CARLA", "add a carla_msgs type", "why is my type hash warning appearing", or needs a message CARLA does not publish yet. There is no IDL codegen — every step is manual.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

carla-simulator/carla-agentic-tools42026년 9월 12일 업데이트

Adds a new topic to CARLA's native ROS 2 interface — a publisher (BasePublisher + PublisherImpl, topic suffix, QoS, registration in ROS2::GetOrCreateSensor, a ProcessDataFrom* entry point and its call site in the UE4 plugin) or a subscriber that lets ROS drive an actor. Also covers adding a middleware (RMW) behind IPublisherMiddleware. Use when the user asks to "publish X to ROS from CARLA", "add a ROS topic/publisher/subscriber", "make the obstacle/lane-invasion sensor publish", "add odometry to ROS", or "add another RMW".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

carla-simulator/carla-agentic-tools42026년 9월 12일 업데이트

Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result files, and the criteria JSON written alongside a --record recording — and runs the metrics module (metrics_manager.py) to compute custom measurements over a recorded run offline, without the simulator. Use when the user asks "did the scenario pass", "why did it fail", "summarise these results", "compare these runs", or wants distance/speed/lane metrics from a recording.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

carla-simulator/carla-agentic-tools42026년 9월 12일 업데이트

Gets actor and level 3D bounding boxes and projects them into a camera image as 2D boxes — the dataset-annotation workflow. Lists box geometry, draws 3D boxes in the world via debug, or captures one camera frame and writes an annotated PNG plus a JSON of 2D boxes for matching actors. Use when the user asks to "get bounding boxes", "draw boxes around the cars", "project boxes onto the camera", or "generate a detection dataset / annotations".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

carla-simulator/carla-agentic-tools42026년 9월 12일 업데이트

Builds CARLA (branch ue4-dev, Unreal Engine 4.26) from source on Linux end-to-end — UE4 fork, the Carla server (editor C++ modules), the LibCarla Python client wheel, and content — then verifies them against a from-source server. Optionally builds the native ROS 2 interface in (ROS2=1 → --ros2, Fast-DDS/CycloneDDS/Zenoh), which is compile-time only and cannot be enabled later. Use when the user asks to "build CARLA from source", "compile CARLA ue4-dev", "set up CARLA on Ubuntu (incl. 24.04)", "build CARLA with ROS2 support", or "produce a CARLA server + client wheel". Cooking a distributable Dist/ package is a separate skill (package-carla-ue4); running the build is run-carla-server.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

carla-simulator/carla-agentic-tools42026년 9월 12일 업데이트

Builds CARLA on Unreal Engine 5.8 from the ue58-dev branch using its CMake build system — configure a preset, then build the carla-unreal / carla-unreal-editor / carla-python-api-install / launch targets — with ROS 2, DLSS, RSS and cook-scope options, and the engine-side build of the CarlaUnreal UE 5.8 fork. There is no Makefile and no Util/BuildTools in this tree, so every UE4 `make` recipe is invalid here. Use when the user asks to "build CARLA UE5", "build ue58-dev", "compile CARLA with cmake", "rebuild the Python API", or hits a CMake configure or target failure.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

carla-simulator/carla-agentic-tools42026년 9월 12일 업데이트

carla-simulator의 스킬 모두 보기

이 스킬의 문제 신고