Patent · US Active

Physical model and machine learning combined method to simulate autonomous vehicle movement

US10343685B2 · kind B2 · utility

8Cited by
9References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 28, 2016
Grant dateJul 9, 2019
Priority date
Expiry dateFeb 5, 2037

Classification

  • Technology area (CPC B)Performing Operations; Transporting
  • CPC primaryB60W2720/20
  • WIPO fieldTransport
  • WIPO sectorMechanical engineering

Abstract

In one embodiment, a driving scenario is identified for a next movement for an autonomous vehicle, where the driving scenario is represented by a set of one or more predetermined parameters. A first next movement is calculated for the autonomous vehicle using a physical model corresponding to the driving scenario. A sideslip predictive model is applied to the set of predetermined parameters to predict a sideslip of the autonomous vehicle under the driving scenario. A second next movement of the autonomous vehicle is determined based on the first next movement and the predicted sideslip of the autonomous vehicle. The predicted sideslip is utilized to modify the first next movement to compensate the sideslip. Planning and control data is generated for the second next movement and the autonomous vehicle is controlled and driven based on the planning and control data.

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