pdm-lite
Datasets
All datasets matching “pdm-lite”PDM_Lite_Carla_LB2
PDM-Lite Dataset for CARLA Leaderboard 2.0
Description
PDM-Lite is a state-of-the-art rule-based expert system for autonomous urban driving in CARLA Leaderboard 2.0, and the first to successfully navigate all scenarios. This dataset was used to create the QA dataset for DriveLM-Carla, a benchmark for evaluating end-to-end autonomous driving algorithms with Graph Visual Question Answering (GVQA). DriveLM introduces GVQA as a novel approach, modeling perception, prediction… See the full description on the dataset page: https://huggingface.co/datasets/autonomousvision/PDM_Lite_Carla_LB2.AD_pdm-lite_carla-lb2This is just a reproduction of https://huggingface.co/datasets/autonomousvision/PDM_Lite_Carla_LB2.
PDM-Lite-DVS
PDM-Lite-DVS
PDM-Lite-DVS is an independently collected synthetic CARLA 0.9.15 event-camera
dataset generated with the rule-based PDM-Lite expert on route configurations
published by carla_garage. The release lineage is 5,545 public route XMLs →
5,503 recordings in the frozen local pool → 257 rejected recordings → 5,246
published recordings. “Public route release” refers only to the route
configurations: the sensor measurements are an independent collection. This
is not the… See the full description on the dataset page: https://huggingface.co/datasets/SamanthaZhang/PDM-Lite-DVS.pdm_lite_3textpdmliteAutoMoT-PDM-Lite-BEV-Encoder-Indexes
AutoMoT PDM-Lite BEV Encoder Indexes
This dataset provides the prepared PDM-Lite JSONL indexes for AutoMoT training.
Files
pdm_lite_2hz_2tp_train_bev_encoder.jsonl
pdm_lite_2hz_2tp_val_bev_encoder.jsonl
Each row contains four historical front-camera paths in image, the current
front-camera path in front, trajectory and route supervision, future-speed
supervision, and a reference to the precomputed current-frame BEV feature:
bev_encoder_feature… See the full description on the dataset page: https://huggingface.co/datasets/HqH1111/AutoMoT-PDM-Lite-BEV-Encoder-Indexes.