Gm global technology operations llc (20240249534). LANE EDGE FUSION SYSTEM FOR AN AUTONOMOUS VEHICLE simplified abstract

From WikiPatents
Jump to navigation Jump to search

LANE EDGE FUSION SYSTEM FOR AN AUTONOMOUS VEHICLE

Organization Name

gm global technology operations llc

Inventor(s)

Brent Navin Roger Bacchus of Sterling Heights MI (US)

LANE EDGE FUSION SYSTEM FOR AN AUTONOMOUS VEHICLE - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240249534 titled 'LANE EDGE FUSION SYSTEM FOR AN AUTONOMOUS VEHICLE

Simplified Explanation:

The patent application describes a system for an autonomous vehicle that fuses lane edge data from perception and map sources to improve navigation accuracy.

  • The system uses perception data and map data to identify lane edge points on the roadway.
  • It selects an evaluation point based on these lane edge points.
  • An implicit function is derived for the evaluation point using a moving least squares approach.
  • A fused lane edge is created by setting a point on the implicit curve as one of the fused lane edge points.

Key Features and Innovation:

  • Integration of perception and map data for lane edge fusion.
  • Use of an implicit moving least squares approach for curve fitting.
  • Creation of a fused lane edge for improved navigation accuracy.

Potential Applications:

  • Autonomous vehicles for improved lane detection and navigation.
  • Advanced driver assistance systems for enhanced safety on the road.

Problems Solved:

  • Inaccuracies in lane detection and navigation for autonomous vehicles.
  • Limited reliability of perception data alone for lane edge identification.

Benefits:

  • Enhanced accuracy in lane detection and navigation.
  • Improved safety and efficiency for autonomous vehicles.

Commercial Applications:

Lane edge fusion technology can be utilized in the development of autonomous vehicles, advanced driver assistance systems, and smart transportation infrastructure. This innovation has the potential to revolutionize the way vehicles navigate roads and enhance overall road safety.

Questions about Lane Edge Fusion:

1. How does the implicit moving least squares approach improve lane edge fusion accuracy? 2. What are the main challenges in implementing lane edge fusion technology in real-world autonomous vehicles?


Original Abstract Submitted

a lane edge fusion system for an autonomous vehicle includes one or more controllers executing instructions to receive perception data and map data of a roadway the autonomous vehicle is traveling along. the one or more controllers derive a plurality of map lane edge points from the map data and a plurality of perception lane edge points from the perception data and select an evaluation point based on the plurality of map lane edge points and the plurality of perception lane edge points. the one or more controllers fit an implicit function for the evaluation point based on an implicit moving least squares approach. the one or more controllers build a fused lane edge by setting a point on the implicit curve as one of a plurality fused lane edge points.