跳到正文
cccskills
免费在 GitHub 公开

query-recording

Inspects a recorded CARLA .log without replaying it — show_recorder_file_info for the header/actors/frames, collision queries between actor categories, and blocked-actor queries for vehicles that got stuck. Use when the user asks to "what's in this recording", "show recorder info", "which vehicles collided", "find collisions in the log", or "which actors were blocked/stuck".

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(5)

  • SKILL.md4.0 KB
  • references/queries.md2.1 KB
  • scripts/check_env.sh2.1 KB
  • scripts/env.sh1.3 KB
  • scripts/query.py3.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Query a CARLA recording

Paths. scripts/… and references/… below are relative to the directory holding this SKILL.md. Your working directory is the user's project, not that directory, so prefix them with its absolute path or the command is not found.

Read facts out of a .log without replaying it. The server parses the file and returns a text report. Three questions:

  • What's in it? — info (header: map, duration, frames, actor list).
  • What crashed? — collisions between two actor categories.
  • What got stuck? — blocked actors that barely moved.

Instructions

Progress:
- [ ] Step 1: Check prerequisites (bash scripts/check_env.sh), clear FAILs
- [ ] Step 2: Run the query that answers the question (info / collisions / blocked)
- [ ] Step 3: Read the report; use ids/times to drive a targeted replay if needed

Commands need CARLA_HOST/CARLA_PORT from scripts/env.sh.

Step 1: Check prerequisites

bash scripts/check_env.sh

Step 2: Query

source scripts/env.sh

# header + actors (add --all for every frame; large)
python3 scripts/query.py info --file /tmp/run.log

# collisions: category codes h=hero v=vehicle w=walker t=traffic-light o=other a=any
python3 scripts/query.py collisions --file /tmp/run.log --type1 v --type2 a   # any vehicle vs anything
python3 scripts/query.py collisions --file /tmp/run.log --type1 v --type2 w   # vehicle vs walker

# actors that moved < 1 m (100 cm) over >= 30 s (stuck)
python3 scripts/query.py blocked --file /tmp/run.log --min-time 30 --min-distance 100

Units matter: --min-time is seconds, --min-distance is centimetres (100 = 1 m).

Step 3: Act on it

The reports give frames, times and actor ids — feed them to replay-recording (--start, --follow) to jump to and watch the interesting moment.

Examples

Example 1: overview

User says: "what's in /tmp/run.log?"

info --file /tmp/run.log → map, duration, frame count, actors.

Example 2: find a crash

User says: "did any car hit a pedestrian?"

collisions --file /tmp/run.log --type1 v --type2 w. Each line gives the frame, time and the two actor ids; then replay play --start <t> --follow <id>.

Example 3: find gridlock

User says: "which cars got stuck?"

blocked --file /tmp/run.log --min-time 20 --min-distance 50 (moved < 0.5 m in 20 s).

Troubleshooting

Problem: parse error / empty report Cause: the .log is not on the server at that path, or has no frames. Solution: use the server-side path; confirm the recording with info first.

Problem: collisions returns nothing but I saw a crash Cause: wrong categories, or collisions need additional_data context. Solution: widen with --type2 a (any); ensure the recording captured the actors.

Problem: blocked lists everything / nothing Cause: --min-distance unit confusion (centimetres, not metres). Solution: 100 = 1 m; raise --min-time to ignore brief stops at lights.

Outputs

Text reports printed to stdout (no world change, no file written). Use them to target a replay-recording.

Detail (report fields, category codes, blocked-query semantics) in references/queries.md.

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示原文说明。

carla-simulator/carla-agentic-tools42026年9月12日 更新

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".

中文简介正在准备中。当前显示原文说明。

carla-simulator/carla-agentic-tools42026年9月12日 更新

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.

中文简介正在准备中。当前显示原文说明。

carla-simulator/carla-agentic-tools42026年9月12日 更新

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".

中文简介正在准备中。当前显示原文说明。

carla-simulator/carla-agentic-tools42026年9月12日 更新

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.

中文简介正在准备中。当前显示原文说明。

carla-simulator/carla-agentic-tools42026年9月12日 更新

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.

中文简介正在准备中。当前显示原文说明。

carla-simulator/carla-agentic-tools42026年9月12日 更新

查看 carla-simulator 的全部技能

报告此技能的问题