Embodied AI
AgiBot World
Manipulation
- Cutting-edge Sensor and Hardware Design.
- Wide-spectrum of Scenario Coverage.
- Quality Assurance with Human-in-the-loop.
Autonomous Driving
OpenDV
Generation
World Model
- The largest driving video dataset to date, containing more than 1700 hours of real-world driving videos.
DriveLM
Language
Planning
- ECCV 2024 Oral.
- Driving with Graph Visual Question Answering.
- Facilitating the Perception, Prediction, Planning, Behavior, Motion tasks with human-written reasoning logic as a connection in between.
-
Autonomous Grand Challenge @ CVPR 2024with 152 teams from 14 countries and regions participating.
OpenScene
Occupancy
- Covering a wide span of over 120 hours and providing occupancy labels collected in various cities.
-
Autonomous Grand Challenge @ CVPR 2024with 212 teams from 13 countries and regions participating.
OpenLane-V2
Topology Recognition
3D Lane Detection
Traffic Element Recognition
- The world's first perception and reasoning benchmark for scene structure in autonomous driving.
-
Autonomous Grand Challenge @ CVPR 2024with 120 teams from 10 countries and regions participating. -
Autonomous Driving Challenge @ CVPR 2023with 34 teams from 4 countries and regions participating.
OpenLane
3D Lane Detection
- ECCV 2022 Oral.
- The first real-world and the largest scaled 3D lane dataset to date.
- Owning 200K frames and over 880K lanes.
