Views
No views yet
| Single-Process Integration | CARLA + AirSim in one UE4 process. No bridge, no latency. Only 3 upstream files modified (~35 lines). |
| Dual Python API | carla.Client (port 2000) + airsim.MultirotorClient (port 41451) in one script. 89/89 CARLA API tests passing. |
| Up to 18 Sensor Modalities | RGB, Depth, Semantic Seg, LiDAR, Radar, IMU, GNSS, and more — all frame-aligned across air and ground. |
| ~20 FPS Joint Workloads | 19.8 ± 1.1 FPS with vehicles + drone + 8 sensors. Communication overhead < 0.5 ms. |
| 3-Hour Stability | 357 spawn/destroy cycles, zero crashes, zero memory accumulation. |
| 63 ROS 2 Topics | Full ROS 2 support across both simulation backends. |
| File | Size | Description |
|---|---|---|
CarlaAir-v0.1.7.zip | ~6.4 GB | Complete binary release (Ubuntu 20.04 / 22.04) |
1# 1. Download and extract
2# Download CarlaAir-v0.1.7.zip from the Files tab above
3unzip CarlaAir-v0.1.7.zip
4cd CarlaAir-v0.1.7
5
6# 2. One-click environment setup
7bash env_setup/setup_env.sh
8conda activate carlaAir
9bash env_setup/test_env.sh
10
11# 3. Launch the simulator
12./CarlaAir.sh Town10HD
13
14# 4. Run the showcase (in another terminal)
15conda activate carlaAir
16python3 examples/quick_start_showcase.py1@article{zeng2026carlaair,
2 title = {CARLA-Air: Fly Drones Inside a CARLA World --
3 A Unified Infrastructure for Air-Ground Embodied Intelligence},
4 author = {Zeng, Tianle and Chen, Hanxuan and Wen, Yanci and Zhang, Hong},
5 journal = {arXiv preprint arXiv:2603.28032},
6 year = {2026}
7}