When I tried to import a clip from the PhysicalAI-Autonomous-Vehicles-NuRec 26.02 dataset into CARLA, I entered the following command in the terminal
python3 example_nurec_replay_save_images.py --usdz-filename /home/data1/NuRec/25cd4769-5dcf-4b53-a351-bf2c5deb6124.usdz
It returned the following error
2026-05-18 15:02:09 INFO Killing old NuRec containers with same image: ['NuRec_clipgt-001b28cb-b8f7-4627-ae65-fda88612d5bf_run_8badb53a']
2026-05-18 15:02:13 INFO CUDA_VISIBLE_DEVICES not set, defaulting to GPU 0
2026-05-18 15:02:13 INFO Starting container NuRec_pai_25cd4769-5dcf-4b53-a351-bf2c5deb6124_run_015d3f7e on localhost:46435
2026-05-18 15:02:13 INFO Waiting for server to start and scene to load...
2026-05-18 15:02:45 ERROR Critical error detected: [2026-05-18 07:02:45,165][nre.grpc.serve][ERROR] Failed to create backend for pai_25cd4769-5dcf-4b53-a351-bf2c5deb6124: Unknown calib name='free-pose-calib'.
2026-05-18 15:02:45 ERROR Timeout waiting for server to be ready
Traceback (most recent call last):
File "/home/data1/CARLA_pre/PythonAPI/examples/nvidia/nurec/example_nurec_replay_save_images.py", line 333, in <module>
main()
File "/home/data1/CARLA_pre/PythonAPI/examples/nvidia/nurec/example_nurec_replay_save_images.py", line 286, in main
with NurecScenario(
File "/home/data1/CARLA_pre/PythonAPI/examples/nvidia/nurec/nurec_integration.py", line 695, in __enter__
super().__enter__()
File "/home//data1/CARLA_pre/PythonAPI/examples/nvidia/nurec/nurec_render_service.py", line 516, in __enter__
self.start()
File "/home/data1/CARLA_pre/PythonAPI/examples/nvidia/nurec/nurec_render_service.py", line 500, in start
raise RuntimeError("Server failed to start properly")
RuntimeError: Server failed to start properly
However, importing clips from the PhysicalAI-Autonomous-Vehicles-NuRec 25.07 dataset into CARLA works perfectly without any issues.
What causes this issue and how can I fix it? Additionally, I have reconstructed my self-collected dataset into USDZ files following the guidelines at https://docs.nvidia.com/nurec/nurec/model.html, and these files can render images normally. However, since I am using the Docker image nvcr.io/nvidia/nre/nre-ga:26.02.00, I encounter the same error mentioned above when importing my custom reconstructed USDZ files. How should I resolve this problem?