Pictura: GPU-accelerated multi-agent simulator trains driving policies via camera-only self-play
abursuc · x · 2026-09-05
Researchers unveil Pictura, a GPU-accelerated multi-agent driving simulator that rapidly renders every agent's ego-centric view at each timestep.
Prior self-play driving agents relied on a shortcut: privileged access to every vehicle's position and speed, even ones they couldn't see — information a real car never gets. Pictura removes it, enabling large-scale self-play training of driving policies using only camera input, without privileged information.
More from Embodied
- XPeng commissions 80%-automated line for IRON humanoid, mass production by end-2026 — ingliguori · 2026-10-23
- HKU's TILDE Distills Embodied Foundation Models into Robot Policies — hkuhk · 2026-10-23
- 10 of 12 Beta Robots Worked Without Fine-Tuning — Do We Still Need It? — micoolcho · 2026-10-23
- EmbodiedEvo lets robot agents self-train, banking reusable Skills and Lessons across tasks — jiqizhixin · 2026-10-23
- KAIST's FRED lifts robot policy success from 19.4% to 50% via self-distilled future video representations — kaist-ai · 2026-10-23
- GALAX Launches World's First RTX 5080 With Dual 12V-2x6 Connectors at $3000 — chemist_slime · 2026-10-23