ColaVLA
[CVPR2026] ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving & [CVPR2025] SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving
File Explorer
Download Latest Version (.zip)- close-loop-results.png
- framework.png
- illustrate.png
- illustrate_hr.jpg
- open_loop_results.png
- visualization.png
- merge_trajproj.pth
- pretrain_qformer
- solve_kmeans_plan_36.npy
- traj_queries.pt
- kmeans_plan_ego_div6.npy
- nuscenes
- nuScenes-Occupancy
- nuscmap_extractor.py
- trajectory_api.py
- utils.py
- environment.yml
- setup.md
- train_infer.md
- __init__.py
- eval_planning_pkl.py
- map_api.py
- planning_utils.py
- inference_vla.py
- inference_vlm.py
- __init__.py
- check_server.py
- data_types.py
- run_colavla_vla.sh
- run_local_colavla.sh
- runner.py
- server.py
- colavla_epoch10_msarplv2_ms6_seqformer_wckpt_fullcontext_regw80_pretraintraj_globalreason_top3pred.py
- solve_vlm_seq_384_cot_rag5_loade6qformere2e0320_noqa_headlr20_e10_cotspeed.py
- __init__.py
- mmdet_train.py
- test.py
- train.py
- __init__.py
- hungarian_assigner_2d.py
- hungarian_assigner_3d.py
- map_assigner.py
- __init__.py
- nms_free_coder.py
- __init__.py
- match_cost.py
- util.py
- __init__.py
- eval_hooks.py
- __init__.py
- optimizer.py
- __init__.py
- formating.py
- load_nuscenes_occ.py
- load_nuscenes_openocc.py
- transform_3d.py
- __init__.py
- distributed_sampler.py
- group_sampler.py
- sampler.py
- __init__.py
- constants.py
- conversation.py
- data_utils.py
- __init__.py
- builder.py
- nuscenes_dataset.py
- nuscenes_dataset_constructive.py
- __init__.py
- attention.py
- block.py
- dino_head.py
- ffn_layers.py
- fp8_linear.py
- layer_scale.py
- patch_embed.py
- rms_norm.py
- rope_position_encoding.py
- sparse_linear.py
- __init__.py
- cluster.py
- custom_callable.py
- dtype.py
- utils.py
- __init__.py
- eva_vit.py
- vision_transformer.py
- vovnet.py
- vovnetcp.py
- __init__.py
- focal_head.py
- image_head.py
- llava_arch.py
- llava_llama.py
- petr_head_map.py
- petr_head_map_with_img.py
- planning_head.py
- streampetr_head.py
- streampetr_head_with_img.py
- __init__.py
- action_head.py
- classifier.py
- petr3d.py
- petr3d_classify_msar_parallel_seqformer_v2.py
- petr3d_image_seq_e2e_cot.py
- __init__.py
- map_loss.py
- __init__.py
- cp_fpn.py
- __init__.py
- attention.py
- cache_utils.py
- grid_mask.py
- layer_decay_optimizer_constructor.py
- logging.py
- misc.py
- modeling_attn_mask_utils.py
- modeling_gguf_pytorch_utils.py
- petr_transformer copy.py
- petr_transformer.py
- positional_encoding.py
- __init__.py
- __init__.py
- __init__.py
- nuscenes_converter.py
- create_data_nusc.py
- dist_test.sh
- dist_train.sh
- merge_prediction_results.py
- multi_dist_train.sh
- test.py
- train.py
- visual_nuscenes.py
- visualize.py
- launch_test.sh
- launch_train.sh
- LICENSE
- README.md
- requirements.txt
# Installation Guide
1. Get the code
git clone https://github.com/pqh22/ColaVLA
Downloads the entire project code from GitHub to your computer.
cd ColaVLA
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
python <μ€νν νμΌλͺ
>.py # READMEμμ μ νν μ€ν νμΌλͺ
μ νμΈνμΈμ
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
// repository documentation
Was this content helpful?
(0 ratings)