Apollo World: Baidu's AI world model that simulates 100,000 km of robotaxi driving a day
Baidu's Apollo World generates real-time multimodal driving simulations, including camera and lidar streams, to train robotaxi systems, producing up to 100,000 km of simulated driving daily.
Why it matters
It turns robotaxi training from road miles into generated miles, and Baidu says it is already being used to train Apollo Go's fleet.
What you could build with it
An autonomous-vehicle startup could generate edge-case driving scenarios in simulation, such as sudden jaywalkers, construction zones and rare weather, to test a perception stack before road trials, cutting the cost of collecting rare real-world miles.
Does it hold up?
Too early to judge: launched today with vendor-reported simulation volumes only, and no public demo or independent evaluation was available at ingest time.
Built with Apollo World
- China's Baidu launches AI model simulating road environment for robotaxisarticle · Reuters report on Apollo World's launch, its 100,000 km-a-day simulated driving, and its use in training Apollo Go's robotaxi fleet.
- Baidu launches Apollo World model to train robotaxis in simulated environmentstechnode · TechNode's report on Apollo World's interactive road environments, real-time camera and lidar output, and use in Apollo Go's global robotaxi development.
- Baidu's new AI simulator gives robotaxis a crash course in rare road hazardsscmp · SCMP coverage of the Shenzhen AI Day demos, including cyclists cutting across intersections and dogs running into a robotaxi's path.
- China's Baidu launches AI model simulating road environment for robotaxisreuters · Reuters on Apollo World's 100,000 km-a-day simulated driving claim and its role training Apollo Go's fleet for global operation.
Learn more
First spotted on article: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72NVIDIA Cosmos 3.5 world models: now openly availableNVIDIA's Cosmos 3.5 family of open world foundation models for robots, autonomous vehicles and vision agents is now…models · JEV 0.71
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.