Create, migrate, refine, or debug CARLA vehicle assets with Blender and Unreal. Use real vehicle references to guide geometry and materials, configure wheels, lights, and physics, and deliver editable sources with evidence from runtime validation.
中文简介正在准备中。当前显示英语简介。
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.
安装前可以查看交给 AI 代理的指令内容。
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.
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.
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.
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.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Add a message type to CARLA's native ROS 2 interface. Create its C++ data structure, serialization code for transmission, type identity hash, registration, and tests, with Docker-based hash calculation and build checks.
中文简介正在准备中。当前显示英语简介。
Extend CARLA’s native ROS 2 interface to publish sensor data or receive vehicle commands. Covers topic implementation, registration, data connections, and verification, plus adding middleware, the communication layer used to exchange messages.
中文简介正在准备中。当前显示英语简介。
Summarize ScenarioRunner results to see which scenarios passed and which checks failed. Compare runs before and after changes, or analyze recorded driving to produce measurements and plots of vehicle distance and deviation from the lane center.
中文简介正在准备中。当前显示英语简介。
Checks a local CARLA checkout for missing API documentation, outdated references, broken links, and pages absent from navigation. Produces a grouped Markdown report without building the project or running the simulator.
中文简介正在准备中。当前显示英语简介。
Read and display CARLA object bounding boxes, then project them onto a camera image as 2D rectangles. Export an annotated PNG and box coordinates in JSON for object detection annotation work.
中文简介正在准备中。当前显示英语简介。
Builds CARLA's ue4-dev branch on Linux, producing the Unreal Engine 4.26 editor, server modules, and an installed Python client package. Fetches required content, optionally compiles native ROS 2 support, and verifies the build against a source-built server.
中文简介正在准备中。当前显示英语简介。