17835824. State Identification For Road Actors With Uncertain Measurements Based On Compliant Priors simplified abstract (FORD GLOBAL TECHNOLOGIES, LLC)
Contents
State Identification For Road Actors With Uncertain Measurements Based On Compliant Priors
Organization Name
Inventor(s)
Randall Schur of Pittsburgh PA (US)
Kevin Wyffels of Livonia MI (US)
State Identification For Road Actors With Uncertain Measurements Based On Compliant Priors - A simplified explanation of the abstract
This abstract first appeared for US patent application 17835824 titled 'State Identification For Road Actors With Uncertain Measurements Based On Compliant Priors
Simplified Explanation
The patent application describes a system, method, and computer program for identifying the state of road actors (such as vehicles or pedestrians) with uncertain measurements based on prior information. The system is designed for autonomous vehicles to improve their perception capabilities.
- The perception system of an autonomous vehicle detects an object with an uncertain kinematic state using sensor information.
- Three distributions of velocity values are generated based on sensor information, map information, and the kinematic state of other objects in proximity to the detected object.
- A velocity value for the detected object is determined by comparing the three distributions of velocity values.
- The autonomous vehicle can then perform a driving maneuver based on the velocity value for the detected object.
Potential Applications
This technology has potential applications in various fields, including:
- Autonomous vehicles: The system can enhance the perception capabilities of autonomous vehicles, allowing them to better understand and respond to the behavior of other road actors.
- Traffic management: By accurately identifying the state of road actors, this technology can contribute to improving traffic flow and safety.
Problems Solved
The technology addresses the following problems:
- Uncertain measurements: The system deals with situations where sensor information about the state of road actors is uncertain or noisy.
- Complex environments: The system can handle complex environments with multiple objects in proximity, providing a more accurate understanding of the surrounding traffic.
Benefits
The technology offers several benefits:
- Improved perception: By incorporating prior information and generating distributions of velocity values, the system can provide a more accurate estimation of the state of road actors.
- Enhanced safety: The system enables autonomous vehicles to make informed decisions and perform driving maneuvers based on a better understanding of the behavior of other road actors.
- Efficient traffic flow: Accurate identification of the state of road actors can contribute to smoother traffic flow and reduce the risk of accidents.
Original Abstract Submitted
Disclosed herein are system, method, and computer program product embodiments for state identification for road actors with uncertain measurements based on compliant priors. The perception system of an autonomous vehicle (AV) may detect an object with an uncertain kinematic state based on sensor information received from a sensing device associated with the AV. A first, second, and third distribution of velocity values may be generated based on the sensor information, map information, and a kinematic state for each additional object of a plurality of additional objects in proximity to the detected object with the uncertain kinematic state, respectively. A velocity value for the detected object with the uncertain kinematic state may be generated based on a comparison of the first, second, and third distributions of velocity values. The AV may perform a driving maneuver based on the velocity value for the detected object.
