Computer-implemented method, advanced driver assistance system, and vehicle

JP7755777B2Active Publication Date: 2025-10-17HONDA MOTOR CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2024024540
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2023-03-27
Filing Date
2024-02-21
Publication Date
2025-10-17
Estimated Expiration
2044-02-21

AI Technical Summary

Technical Problem

Existing vehicle assistance systems fail to effectively address black swan events, which are unpredictable and potentially catastrophic events that can lead to severe collisions, due to their reliance on risk models that ignore low-probability but high-consequence behaviors of other agents in dynamic environments.

Method used

A computer-implemented method that detects black swan events by predicting behaviors of other agents, calculating collision probabilities and severities, and triggering a separate short-term planner to adapt the vehicle's behavior to mitigate these events, using a short-term planner in parallel with a long-term planner to enhance situational awareness and response efficiency.

Benefits of technology

The method significantly improves the vehicle's ability to handle dense and dynamic environments by reducing planning complexity, enhancing situational awareness, and enabling earlier response to black swan events, thereby improving safety and operational efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007755777000001
    Figure 0007755777000001
  • Figure 0007755777000002
    Figure 0007755777000002
  • Figure 0007755777000003
    Figure 0007755777000003
Patent Text Reader

Abstract

To improve an assistance system with respect to avoiding collisions or reducing the severity of collisions caused by black swan events created by actions of other agents in an environment of an ego-vehicle.SOLUTION: A computer-implemented method for detecting black-swan events for assisting operation of an ego-agent comprises: sensing an environment of the ego-agent that includes at least one other agent; and predicting actions of the at least one other agent based on the sensed environment. The method includes detecting at least one potential black-swan event in the environment of the ego-agent by determining at least one predicted possible action of the at least one other agent for which a computed situation probability is smaller than a first threshold, a computed collision probability exceeds a second threshold, and determined collision severity exceeds a third threshold.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Apparatus, methods and articles for facilitating motion planning in environments with dynamic obstacles

    JP2022536263A

  • Vehicle control apparatus, vehicle control method, autonomous driving apparatus, and autonomous driving method

    WO2021020311A1