Vehicle Path Control Using Branching-Area Behavior Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver assistance and autonomous driving systems fail to account for potential changes in the driving route of detected objects, leading to increased computational resources and decreased driving comfort, especially in areas like roundabouts and highway approaches.

Innovation Solution

A vehicle travelling control apparatus that includes a localization unit, area prediction unit, object detection unit, and object behavior prediction unit, which determines potential meeting areas and adapts the vehicle's path based on predicted object behavior using map information and sensor data, optimizing computational effort by switching between normal and detailed prediction modes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If detailed analysis of the behavior (manoeuvres) of the detected object is performed, then collision avoidance capability is improved, but computational resources required increase

Engineering Contradiction:
Improvecollision avoidance capabilityVSAvoidcomputational resources
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the prediction process into two distinct modes: normal prediction mode for objects outside the branching area, and detailed prediction mode for objects within the branching area. This segmentation allows the system to apply computational effort selectively - only performing detailed behavior analysis when necessary (when an object is in the branching area), while using simpler prediction for other cases, thus resolving the contradiction between collision avoidance capability and computational resource requirements

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies detailed prediction mode only partially - specifically when a detected object enters the branching area. For all other situations, normal prediction mode suffices. This partial application of detailed analysis ensures high collision avoidance capability when needed while avoiding excessive computational resource consumption during routine operations

Inventive Principle:
Principle #16Partial or excessive action

2Ease of operation

If potential changing manoeuvres of the detected object are taken into account, then driving comfort is improved, but computational resources required increase

Engineering Contradiction:
Improvedriving comfortVSAvoidcomputational resources
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent segments the monitoring space into a branching area (where detailed prediction is applied) and other areas (where normal prediction suffices). This allows the system to account for potential changing maneuvers only when relevant (in the branching area), improving driving comfort through adaptive behavior prediction without continuously consuming high computational resources

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Detailed behavior prediction is applied only partially - when objects are within the branching area where maneuver changes are most relevant to driving comfort. This selective application provides enhanced driving comfort prediction exactly where needed while avoiding unnecessary computational overhead in other situations

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12036982B2Vehicle travelling control apparatus, vehicle travelling control method and computer program product
Publication Date: 2024.07.16 ASTEMO LTD
  • US12036982B2 patent drawing
  • US12036982B2 patent drawing
  • US12036982B2 patent drawing

AI summary

The present subject matter especially relates to a travelling control apparatus, a corresponding travelling control method, an own vehicle including the travelling control apparatus, and a computer program product which is adapted to carry out the travelling control method. There is optimized the use of computational resources and the driving comfort is increased.