跳到正文
cccskills
免费在 GitHub 公开

navigate-to

Drives a vehicle to a destination autonomously using CARLA's navigation agents (BasicAgent/BehaviorAgent/ConstantVelocityAgent), or plans a route between two points with GlobalRoutePlanner. The agent handles routing, obstacle avoidance and traffic-light obedience. Use when the user asks to "drive the ego to (x,y,z)", "navigate to the junction", "go to that location", "plan a route from A to B", or "make the car drive itself somewhere specific". Manual control is control-vehicle; autopilot roaming is control-traffic.

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.md4.6 KB
  • references/navigation.md2.7 KB
  • scripts/check_env.sh2.2 KB
  • scripts/env.sh1.9 KB
  • scripts/navigate.py6.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Navigate a vehicle to a destination

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.

Point-to-point autonomous driving. go drives the ego to a destination with a navigation agent that plans a route and follows it while avoiding obstacles and obeying (or ignoring, on request) traffic lights. route just plans the path.

This is distinct from the sibling driving skills: control-vehicle is manual actuator input; control-traffic is the Traffic Manager making cars roam; this drives one car to a specific place.

Instructions

Progress:
- [ ] Step 1: Check prerequisites (bash scripts/check_env.sh), clear FAILs (incl. agents import)
- [ ] Step 2: Have an ego (spawn-vehicles ego) and a destination (world-data/map-waypoints)
- [ ] Step 3: go (drive) — or route (plan only). Runs a tick loop until arrival/timeout

Commands need CARLA_HOST/CARLA_PORT + CARLA_ROOT from scripts/env.sh. Negative coordinates: use the = form (--to=-24,-57,0.6).

Step 1: Check prerequisites

bash scripts/check_env.sh

FAILs if the agents package isn't importable — set CARLA_ROOT to a carla checkout so PythonAPI/carla/agents is on PYTHONPATH.

Step 3: Navigate

source scripts/env.sh

# plan a route and draw it (no driving)
python3 scripts/navigate.py route --from=0,0,1 --to=-24,-57,1 --draw

# drive the ego there (BasicAgent, obeys lights)
python3 scripts/navigate.py go --to=-24,-57,1 --speed 25

# a cautious/aggressive style
python3 scripts/navigate.py go --to=-24,-57,1 --agent behavior --behavior aggressive

# ignore lights (e.g. an emergency run) and give it more time
python3 scripts/navigate.py go --to=100,20,1 --ignore-lights --seconds 120

go targets the ego (role hero) by default; --id/--filter for another vehicle. It blocks until the car arrives (agent.done()) or --seconds elapses.

Examples

Example 1: drive to a spot

User says: "drive the ego to (−24, −57)"

go --to=-24,-57,1. It plans, drives, and prints "arrived" on success.

Example 2: go to a resolved element

User says: "drive to the 4-way junction in the middle"

map-waypoints junctions --arms 4 → pick its centre → go --to=<centre>.

Example 3: just the route

User says: "what's the route from here to the depot?"

route --from=<here> --to=<depot> --draw → maneuver list + drawn path.

Troubleshooting

Problem: cannot import agents Cause: the agents package (checkout-only) isn't on PYTHONPATH. Solution: set CARLA_ROOT to a carla checkout; env.sh adds PythonAPI/carla.

Problem: it never arrives / stops at timeout Cause: unreachable destination, too little time, or stuck in traffic. Solution: verify the destination is on a road (map-waypoints waypoint), raise --seconds, or --ignore-vehicles to push through.

Problem: the car doesn't move in sync mode Cause: go ticks the world itself in sync mode; if another process also ticks, they fight. Solution: run one ticker. In async it just drives.

Problem: it stops at every red light forever Cause: dense traffic / lights. Solution: --ignore-lights (and/or the control-traffic-lights skill to free them).

Outputs

Server state — the vehicle drives to the destination (or a planned route + drawn overlay for route). No file. go reports arrival or timeout.

Detail (agent types, route planner, run-step loop, sync interaction) in references/navigation.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