Hao Shao

Sorry for that, 10 routes here denotes the route number of the long route. We will fix it in our updated paper in Arxiv.

Hi, Thank you for your interest in our project. A practical workaround is to design some rules manually in the interfuser_agent.py to let the agent move if its speed is...

Hi! 1. The input of the encoder includes the image feature of the front/left/right/focusing view and the LiDAR feature. https://github.com/opendilab/InterFuser/blob/e4f0314482124bb06a475c3f6fb4bfe3a2701c4d/interfuser/timm/models/interfuser.py#L1024 2. The input of the decoder includes query embeddings(waypoints, traffic...

> the input of the encoder is information about the current frame Yes > the input of the decoder is information about future frames No, it mainly includes the information...

Hi! Our framework also predicts the velocity and the heading when detect the other objects. With these information, we can estimate their future positions. If they are far away from...

In our current pipeline, the framework receives single-frame input and predict single-frame output. Or you can refer to ReasonNet to modify the framework to let it predict multiple frames in...

I have experienced this problem, and it is the cause of the program itself. I recommend you: 1. change a gpu with a larger memory 2. do not use the...

https://github.com/carla-simulator/carla/issues/3540#issuecomment-1401669518

Hi! Sorry for the late reply About the **Weather Data**: we use 0-9 and 15-18 for training, the others for testing. I haven't specified the weather conditions for different towns,...

Hi! Your understanding is correct. The "gps_x" and "gps_y" here represent the location given by CARLA Leaderboard. The "x" and "y" here denote the location provided from CARLA simulator.