Generating Potential Accident Scenarios for Autonomous Vehicles Using AI - NVIDIA DRIVE Labs Ep. 27
Testing autonomous vehicles (AVs) in potential near-accident scenarios is critical for evaluating safety, but is difficult and unsafe to do in the real world. In this episode of DRIVE Labs, we discuss a new method from NVIDIA researchers called STRIVE (Stress-Test Drive), which automatically generates potential accident scenarios in simulation for AVs. The key to STRIVE is a generative AI model of traffic trajectories that encourages scenarios to be realistic even when they contain a potential accident. STRIVE produces diverse and plausible potential accident scenarios based on real-world data, allowing us to safely evaluate the planning part of the AV stack at scale in simulation.
00:00:00 - Adversarial Scenario Generation
00:00:05 - Why do we need to generate scenarios automatically?
00:00:20 - Overview of the STRIVE (Stress-Test Drive) method
00:00:40 - Creating potential accidents and solutions with STRIVE
00:01:05 - Modifying a real-world scenario in DRIVE Sim
00:01:51 - Ensuring realistic scenarios using generative AI traffic model
00:02:11 - Find out more
Read more: https://nvda.ws/3Isup58
GitHub: https://github.com/nv-tlabs/STRIVE
Watch the full series here: https://nvda.ws/3lHQP7H
Learn more about DRIVE Labs: https://nvda.ws/36r5c6t
Follow us on social:
Twitter: https://nvda.ws/3LRdkSs
LinkedIn: https://nvda.ws/3wI4kue
Видео Generating Potential Accident Scenarios for Autonomous Vehicles Using AI - NVIDIA DRIVE Labs Ep. 27 канала NVIDIA
00:00:00 - Adversarial Scenario Generation
00:00:05 - Why do we need to generate scenarios automatically?
00:00:20 - Overview of the STRIVE (Stress-Test Drive) method
00:00:40 - Creating potential accidents and solutions with STRIVE
00:01:05 - Modifying a real-world scenario in DRIVE Sim
00:01:51 - Ensuring realistic scenarios using generative AI traffic model
00:02:11 - Find out more
Read more: https://nvda.ws/3Isup58
GitHub: https://github.com/nv-tlabs/STRIVE
Watch the full series here: https://nvda.ws/3lHQP7H
Learn more about DRIVE Labs: https://nvda.ws/36r5c6t
Follow us on social:
Twitter: https://nvda.ws/3LRdkSs
LinkedIn: https://nvda.ws/3wI4kue
Видео Generating Potential Accident Scenarios for Autonomous Vehicles Using AI - NVIDIA DRIVE Labs Ep. 27 канала NVIDIA
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Accelerating Conversational AIHow AI Helps Autonomous Vehicles See Outside the Box - NVIDIA DRIVE Labs Ep. 14CES 2019: NVIDIA on the Show FloorSummit Early Science Video Series: Fusion ResearchAugmenting Radiology with AINVIDIA and Roborace at CES 2018Chaos Group V-Ray GPU Delivers Accelerated CreativityNVIDIA RTX - The Creative Freedom You ImaginedAI-Driven, Physics-Based Character AnimationNVIDIA Research: First Privacy-Preserving Federated Learning System for Medical ImagingNVIDIA DRIVE at CES 2019Win TWO GeForce GTX 1080 Ti cards - Our Gamescom Giveaway!NVIDIA Announces Project HolodeckSummit Early Science Video Series: Enabling Scientific InnovationWhat Is Computer Vision & Why Does It Matter?GeForce GTX 660 Ti Launch VideoTransforming Graphics with AI | I AM AIAccelerating Lighting and LookDev with NVIDIA Quadro RTX and Autodesk Arnold GPUNVIDIA DGX SuperPODVR Content Showcase Winner: NurulizeGeForce Garage: Cross Desk Series, Video 6 – How To Fill and Leak Test Your Liquid Cooling Loop