Fast Open-Loop and Closed-Loop Simulators for Autonomous Vehicles
summary
Explains why the team simulates a million kilometers per night for autonomous vehicles and compares Open Loop vs Closed Loop simulation use cases. Describes implementing a deterministic, multithreaded ROS-based pipeline and running distributed simulations on YTsaurus.
AI-written summary · about
chapters (8)
- 0:00Introduction to simulators
- 4:20Need for simulator
- 7:55Software components
- 11:03Determinism problem
- 17:31Latency impact matrix
- 22:51Parallel execution
- 27:27Scenario selection and metrics
- 31:59Q&A
related talks
28mOpenAdx "Autonomous Driving Simulation" Testbed – hardware in the loop
15mFrom the Racetrack to the Road - How Open Source Boosts Autonomous Vehicle Development
16m↑↑↓↓← → ← → Autonomous
51mTeaching Autonomous Vehicles to Drive with Visible and Non-Visible Light Simulation
51mOpen space: A revolution in robots for space exploration
31mDeep learning for self-driving vehicle technology
25mDriver Models in SUMO and Elsewhere
01h 51mLearn to Drive (and Race!) Autonomous Vehicles