Daocheng Fu

In lines 314 to 316 of `ExampleLLMAgentCloseLoop.py`, you can see how we get navigation information, action information and environment information. ```Python navInfo = descriptor.getNavigationInfo(roadgraph, vehicles) actionInfo = descriptor.getAvailableActionsInfo(roadgraph, vehicles) envInfo...

`ExampleLLMAgentCloseLoop.py` will not provide round-view images, you can get camera images from `ExampleVLMAgentCloseLoop.py`

In fact, there is no big difference between the two in terms of interface calls, you can take the interfaces in VLMExample and use them in LLMExample to get the...

Did you set `CARLACosim=True` when you initialize the model? ```Python # init simulation model = Model( egoID=ego_id, netFile=sumo_net_file, rouFile=sumo_rou_file, cfgFile=sumo_cfg_file, dataBase=database, SUMOGUI=sumo_gui, CARLACosim=True, carla_host=carla_host, carla_port=carla_port ) ``` However, I still...

So, can you run the VLMExample successfully? You can just run VLMExample to test that your environment is installed correctly and that the application is running properly, without using VLM...

This is an issue with your OpenAI account, please check your account balance.

You should install `carla` package before you run this code.

LLM inference is slow and the program waits for LLM making an answer before running, so lagging is normal.

Yes, it is a replay video, you can run the `ExampleReplay.py` to view the result.

Hello, it seems that you are using LimSim++. In our sample code, `roadgraph, vehicles = model.exportSce()` exports the road network environment around the current frame EGO and the information of...