20230186646. SYSTEM AND METHOD FOR DETECTING ROAD AND LANE CONNECTIONS AT INTERSECTIONS simplified abstract (GM Global Technology Operations LLC)

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR DETECTING ROAD AND LANE CONNECTIONS AT INTERSECTIONS

Organization Name

GM Global Technology Operations LLC

Inventor(s)

Najah Ghalyan of Austin TX (US)

Kaydee Hartmann of Austin TX (US)

Sean D. Vermillion of Austin TX (US)

Mason D. Gemar of Cedar Park TX (US)

Rajesh Ayyalasomayajula of Austin TX (US)

SYSTEM AND METHOD FOR DETECTING ROAD AND LANE CONNECTIONS AT INTERSECTIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20230186646 titled 'SYSTEM AND METHOD FOR DETECTING ROAD AND LANE CONNECTIONS AT INTERSECTIONS

Simplified Explanation

The patent application describes a method for detecting road edges at a specific intersection using aerial imagery data and vehicle telemetry data. The method involves the use of generative adversarial networks (GANs) and a random forest classifier (RFC) to detect road edges and classify vehicle trajectories, respectively.

  • The method receives aerial imagery data and vehicle telemetry data about a predetermined intersection.
  • Generative adversarial networks (GANs) are used to detect road edges at the intersection.
  • Random forest classifier (RFC) is used to classify each vehicle trajectory passing through the intersection with a unique maneuver label.
  • The maneuver labeling and road edges are used to construct a probabilistic finite state automata (PFSA) to pair inbound and outbound lanes at the intersection.
  • A homotopy model is used to determine lane edges at the intersection.

Potential Applications

This technology has potential applications in various areas, including:

  • Autonomous vehicles: The method can be used to improve the perception and understanding of road edges and lane markings, which is crucial for autonomous vehicles to navigate intersections safely.
  • Traffic management: By accurately detecting road edges and classifying vehicle trajectories, the method can help optimize traffic flow and improve intersection management.
  • Urban planning: The data obtained from this method can be used to analyze traffic patterns and make informed decisions for urban planning and infrastructure development.

Problems Solved

The method addresses several problems related to road edge detection and intersection analysis:

  • Accurate road edge detection: By utilizing aerial imagery data and GANs, the method can accurately detect road edges, even in complex intersection scenarios.
  • Vehicle trajectory classification: The use of RFC allows for the classification of vehicle trajectories with unique maneuver labels, providing valuable information for intersection analysis.
  • Lane pairing at intersections: The construction of a PFSA using maneuver labeling and road edges helps pair inbound and outbound lanes, enabling a better understanding of intersection dynamics.

Benefits

The technology offers several benefits:

  • Improved intersection safety: Accurate road edge detection and vehicle trajectory classification can enhance the safety of intersections, especially for autonomous vehicles.
  • Enhanced traffic flow: By optimizing lane pairing and intersection management, the method can contribute to smoother traffic flow and reduced congestion.
  • Efficient urban planning: The data obtained from this method can provide valuable insights for urban planners, helping them make informed decisions for infrastructure development and traffic management.


Original Abstract Submitted

a method for detecting road edges at a predetermined intersection, comprising: receiving, by the controller, aerial imagery data about the predetermined intersection; receiving, by the controller, vehicle telemetry data from at least one vehicle passing through the predetermined intersection; detecting, using the aerial imagery data and generative adversarial networks (gans) executed on the controller, road edges at the predetermined intersection; classifying, using the vehicle telemetry data and a random forest classifier (rfc) executed on the controller, each vehicle trajectory passing through the predetermined intersection with a label corresponding to a unique maneuver to create a maneuver labeling at the predetermined intersection; constructing, using the maneuver labeling determined by the rfc and the road edges, a probabilistic finite state automata (pfsa) to pair inbound lanes with outbound lanes at the predetermined intersection; and determining lane edges at the predetermined intersection using a homotopy model.

Retrieved from "http://wikipatents.org/index.php?title=20230186646._SYSTEM_AND_METHOD_FOR_DETECTING_ROAD_AND_LANE_CONNECTIONS_AT_INTERSECTIONS_simplified_abstract_(GM_Global_Technology_Operations_LLC)&oldid=25970"