Top-down scene discrimination

US11858514B2 · kind B2 · utility

Assignee

• Zoox, Inc. · US

Inventors

• Gerrit Bagschik · Foster City, US
• Andrew Scott Crego · Foster City, US
• Gowtham Garimella · Hayward, US
• Michael Haggblade · San Bruno, US
• Andraz Kavalar · San Francisco, US
• Kai Zhenyu Wang · Burnaby, CA

Key dates

• Filing date: Mar 30, 2021
• Grant date: Jan 2, 2024
• Expiry date: Dec 3, 2041

Classification

• Technology area (CPC B): Performing Operations; Transporting
• CPC primary: B60W2556/10
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Techniques for top-down scene discrimination are discussed. A system receives scene data associated with an environment proximate a vehicle. The scene data is input to a convolutional neural network (CNN) discriminator trained using a generator and a classification of the output of the CNN discriminator. The CNN discriminator generates an indication of whether the scene data is a generated scene or a captured scene. If the scene data is data generated scene, the system generates a caution notification indicating that a current environmental situation is different from any previous situations. Additionally, the caution notification is communicated to at least one of a vehicle system or a remote vehicle monitoring system.