This repository is for the ICCV 2021 paper NEAT: Neural Attention Fields for End-to-End Autonomous Driving.
@inproceedings{Chitta2021ICCV,
author = {Chitta, Kashyap and Prakash, Aditya and Geiger, Andreas},
title = {NEAT: Neural Attention Fields for End-to-End Autonomous Driving},
booktitle = {International Conference on Computer Vision (ICCV)},
year = {2021}
}Please follow the installation instructions from our TransFuser repository to set up the CARLA simulator. The conda environment required for NEAT can be installed via:
conda env create -f environment.yml
conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c nvidiaFor running the AIM-VA baseline, you will additionally need to install MMCV and MMSegmentation.
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html
pip install mmsegmentationThe training data is generated using leaderboard/team_code/auto_pilot.py. Data generation requires routes and scenarios. Each route is defined by a sequence of waypoints (and optionally a weather condition) that the agent needs to follow. Each scenario is defined by a trigger transform (location and orientation) and other actors present in that scenario (optional). We provide several routes and scenarios under leaderboard/data/. The TransFuser repository and leaderboard repository provide additional routes and scenario files.
./CarlaUE4.sh --world-port=2000 -openglWithout Docker:
SDL_VIDEODRIVER=offscreen SDL_HINT_CUDA_DEVICE=0 ./CarlaUE4.sh --world-port=2000 -openglWith Docker:
Instructions for setting up docker are available here. Pull the docker image of CARLA 0.9.10.1 docker pull carlasim/carla:0.9.10.1.
Docker 18:
docker run -it --rm -p 2000-2002:2000-2002 --runtime=nvidia -e NVIDIA_VISIBLE_DEVICES=0 carlasim/carla:0.9.10.1 ./CarlaUE4.sh --world-port=2000 -openglDocker 19:
docker run -it --rm --net=host --gpus '"device=0"' carlasim/carla:0.9.10.1 ./CarlaUE4.sh --world-port=2000 -openglIf the docker container doesn't start properly then add another environment variable -e SDL_AUDIODRIVER=dsp.
Once the CARLA server is running, rollout the autopilot to start data generation.
./leaderboard/scripts/run_evaluation.shThe expert agent used for data generation is defined in leaderboard/team_code/auto_pilot.py. Different variables which need to be set are specified in leaderboard/scripts/run_evaluation.sh. The expert agent is originally based on the autopilot from this codebase.
The training code and pretrained models are provided below.
mkdir model_ckpt
wget https://s3.eu-central-1.amazonaws.com/avg-projects/neat/models.zip -P model_ckpt
unzip model_ckpt/models.zip -d model_ckpt/
rm model_ckpt/models.zipThere are 5 pretrained models provided in model_ckpt/:
- AIM-MT (2D):
aim_mt_semandaim_mt_sem_depth - AIM-MT (BEV):
aim_mt_bev - AIM-VA:
aim_va - NEAT:
neat
Additional baselines are available in the TransFuser repository.
Spin up a CARLA server (described above) and run the required agent. The required variables need to be set in leaderboard/scripts/run_evaluation.sh.
CUDA_VISIBLE_DEVICES=0 ./leaderboard/scripts/run_evaluation.shThis implementation primarily extends the cvpr2021 branch of the existing TransFuser repository.
If you found our work interesting, check out the code for some more recent work on CARLA from our group:
- Renz et al., PlanT: Explainable Planning Transformers via Object-Level Representations (CoRL 2022)
- Chitta et al., TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving (PAMI 2022)
- Hanselmann et al., KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients (ECCV 2022)
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent