18313843. METHOD FOR CLASSIFYING A BEHAVIOR OF A ROAD USER AND METHOD FOR CONTROLLING AN EGO VEHICLE simplified abstract (Robert Bosch GmbH)
Contents
METHOD FOR CLASSIFYING A BEHAVIOR OF A ROAD USER AND METHOD FOR CONTROLLING AN EGO VEHICLE
Organization Name
Inventor(s)
Andreas Schmidt of Stuttgart (DE)
Koba Natroshvili of Waldbronn (DE)
Maxim Dolgov of Renningen (DE)
Steffen Knoop of Hohenwettersbach (DE)
METHOD FOR CLASSIFYING A BEHAVIOR OF A ROAD USER AND METHOD FOR CONTROLLING AN EGO VEHICLE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18313843 titled 'METHOD FOR CLASSIFYING A BEHAVIOR OF A ROAD USER AND METHOD FOR CONTROLLING AN EGO VEHICLE
Simplified Explanation
The patent application describes a method for classifying the driving behavior of a road user in relation to an ego vehicle. Here is a simplified explanation of the abstract:
- The method involves receiving trajectory data of a road user's driving trajectory in the environment of an ego vehicle.
- A latent-space representation of the road user's driving trajectory is determined in a latent space.
- The distance between the latent-space representation of the road user's driving trajectory and the latent-space representation of at least one normal trajectory is calculated.
- If the distance falls below a predetermined limit value, the driving behavior is classified as normal.
- If the distance exceeds the limit value, the driving behavior is classified as abnormal.
Potential applications of this technology:
- Autonomous vehicles: The method can be used to classify the driving behavior of other road users, helping autonomous vehicles understand and predict their actions.
- Driver assistance systems: The method can be utilized in driver assistance systems to detect abnormal driving behaviors and provide warnings or interventions to improve safety.
- Traffic management: By classifying driving behaviors, this technology can contribute to traffic management systems by identifying potential risks or congestion-causing behaviors.
Problems solved by this technology:
- Accurate classification: The method provides a systematic approach to classify driving behaviors, enabling better understanding and prediction of road user actions.
- Early detection of abnormal behaviors: By setting a predetermined limit value, abnormal driving behaviors can be identified early, allowing for timely interventions or warnings.
- Objective assessment: The use of a latent space representation and distance calculation provides an objective measure for classifying driving behaviors, reducing subjective biases.
Benefits of this technology:
- Improved safety: By accurately classifying driving behaviors, this technology can contribute to safer road environments by enabling proactive measures to prevent accidents.
- Enhanced autonomous driving: Autonomous vehicles can benefit from a better understanding of other road users' behaviors, leading to smoother interactions and improved decision-making.
- Efficient traffic management: By identifying abnormal driving behaviors, traffic management systems can take appropriate actions to mitigate risks and optimize traffic flow.
Original Abstract Submitted
A method for classifying a driving behavior of a road user in the environment of an ego vehicle. The method includes: receiving trajectory data of a driving trajectory of a road user arranged in the environment of an ego vehicle; ascertaining a latent-space representation of the driving trajectory of the road user in a latent space; ascertaining a distance of the latent-space representation of the driving trajectory of the road user to a latent-space representation of at least one normal trajectory in the latent space and classifying a driving behavior of the road user as a normal driving behavior if the distance in the latent space falls below a predetermined limit value; or classifying the driving behavior of the road user as an abnormal driving behavior if the distance in the latent space exceeds the predetermined limit value.
