Anthropomorphic Lane-Changing Control via Risk Quantification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing lane-changing behaviors in autonomous driving systems fail to comprehensively consider subjective driving intentions and dynamic influences of surrounding vehicles, leading to safety and user experience issues.

Innovation Solution

An anthropomorphic lane-changing control method that determines lane-changing intentions based on vehicle motion statuses, generates trajectories satisfying safety and reachability constraints, and quantifies risks using a risk field theory, adjusting trajectories if risks are not met, and employs preview-following theory for tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional lane-changing control is used, then the control process is simple, but it fails to comprehensively consider subjective driving intentions and dynamic influences of surrounding vehicles, leading to safety issues

Engineering Contradiction:

Improvelane-changing safetyVSAvoidcontrol process complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The lane-changing control process is segmented into five distinct modules: lane-changing intention decision-making, lane-changing trajectory planning, driving risk quantification, and vehicle motion control. Each module handles specific aspects of the lane-changing process, allowing comprehensive consideration of driving intentions and surrounding vehicle influences while maintaining organized and manageable system complexity

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

A risk field theory model is introduced as an intermediary to quantify the dynamic impact of surrounding vehicles. This risk field serves as a mediator that translates complex environmental factors into quantifiable risk values, enabling the system to comprehensively assess safety without directly processing all raw sensor data

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If traditional lane-changing control is used, then the system is simple to operate, but user experience is poor due to inability to capture subjective driving intentions

Engineering Contradiction:

Improvesystem operabilityVSAvoiddriving intention recognition

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system continuously monitors vehicle motion statuses (position, speed, acceleration) and surrounding environment, feeding this information back to the intention decision-making module. This feedback mechanism enables the system to accurately recognize subjective driving intentions by analyzing patterns in vehicle dynamics and environmental context, while maintaining ease of operation through automated decision-making

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The lane-changing intention decision-making module performs preliminary analysis of driving intentions before actual lane-changing execution. By pre-assessing driver intentions based on motion status feedback and environmental factors, the system adapts the control strategy in advance, improving both user experience and operational smoothness

Inventive Principle:

Principle #10Preliminary action

3Reliability

If risk quantification is added to lane-changing control, then safety is improved, but computational complexity and processing time increase

Engineering Contradiction:

Improvelane-changing safetyVSAvoidtrajectory regeneration time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The risk field theory model calculates risk values for surrounding vehicles selectively based on their relevance to the lane-changing maneuver. Rather than comprehensively analyzing all possible risk factors, the system focuses on partial but critical risk elements (position, speed, acceleration of surrounding vehicles), achieving sufficient safety assessment with reduced computational overhead

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system dynamically adjusts risk assessment parameters based on the current driving context. When regenerating trajectories due to risk constraints, the risk field model updates its parameters (risk values, field boundaries) according to the new trajectory candidates, enabling efficient re-evaluation without full recalculation and reducing overall processing time

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250304071A1Anthropomorphic lane-changing control method and system based on driving risk quantification, and vehicle

Publication Date: 2025.10.02 CHONGQING RESEARCH INSTITUTE JILIN UNIVERSITY

AI summary

The present disclosure discloses an anthropomorphic lane-changing control method and system based on driving risk quantification, and a vehicle. The method includes: determining whether a main vehicle has a lane-changing intention based on motion statuses of the main vehicle and a front vehicle in a current lane; if there is a lane-changing intention, generating an anthropomorphic lane-changing trajectory that satisfies safety constraints and reachability constraints; based on a motion status of a traffic participant that causes a risk to the main vehicle, calculating an overall risk level and determining whether the anthropomorphic lane-changing trajectory satisfies risk constraints; and if the risk constraints are not satisfied, regenerating an anthropomorphic lane-changing trajectory; or if the risk constraints are satisfied, performing tracking control based on a preview-following theory. In the present disclosure, a lane-changing intention is described and identified based on actually measured data, to generate an anthropomorphic lane-changing trajectory.