StandardE2E: A Unified Framework for End-to-End Autonomous Driving Datasets
Researchers have introduced several new approaches to enhance autonomous driving systems. One paper details TaCarla, a large dataset for end-to-end autonomous driving research, featuring over 2.85 million frames and supporting various tasks like detection and prediction. Another study presents the Diffusion Forcing Planner (DFP), a diffusion-based framework designed to improve the temporal consistency and stability of motion plans. Additionally, a new method called Uncertainty-Aware Motion Planning (UAMP) aims to improve safety and comfort in mixed-traffic environments by accounting for uncertainty in human driver intent. AI
IMPACT Advancements in datasets, planning algorithms, and safety frameworks are crucial for accelerating the development and deployment of more robust and reliable autonomous driving systems.
- nuReasoning
- autonomous driving
- nuPlan
- nuScenes
- WayveScenes101
- StandardE2E
- Waymo End-to-End
- Argoverse 2 Sensor
- Waymo Perception
- Argoverse 2 LiDAR
- NAVSIM
- GeoDrive-Bench
- Qwen
- CLEAR
- Drive-JEPA
- RoCA
- Drive-KD
- PLAN-S
- Uncertainty-Aware Motion Planning
- ScenicRules
- ISO 26262
- Diffusion Forcing Planner
- TaCarla
- Qwen 3.5 0.8B
- CARLA
- IGCARL