Drives a CARLA vehicle to a specific destination using navigation agents that plan routes, avoid obstacles, and obey traffic lights. Can also plan and draw a route between two points without moving the vehicle.
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.
Review the instructions the agent will receive before you install.
Paths.
scripts/…andreferences/…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.
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).
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.
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.
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.
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).
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.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
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.
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.
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.
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.
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.
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.