Patent · US Active

Training trajectory scoring neural networks to accurately assign scores

US11586931B2 · kind B2 · utility

2Cited by
6References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 31, 2019
Grant dateFeb 21, 2023
Priority date
Expiry dateMay 4, 2041

Classification

  • Technology area (CPC B)Performing Operations; Transporting
  • CPC primaryB60W60/0011
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network having a plurality of sub neural networks to assign respective confidence scores to one or more candidate future trajectories for an agent. Each confidence score indicates a predicted likelihood that the agent will move along the corresponding candidate future trajectory in the future. In one aspect, a method includes using the first sub neural network to generate a training intermediate representation; using the second sub neural network to generate respective training confidence scores; using a trajectory generation neural network to generate a training trajectory generation output; computing a first loss and a second loss; and determining an update to the current values of the parameters of the first and second sub neural networks.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.