Autonomous Vehicle Lane Change Using Yield Probability Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicles face inefficiencies in lane changes due to environmental vehicles not yielding to the ego vehicle based on turn light signals, often requiring manual intervention or waiting for environmental vehicles to yield.
Innovation Solution
A vehicle-based data processing method and apparatus that determines predicted offsets and payoffs for lane changes, considering the yielding probability of environmental vehicles, to actively occupy their space and improve lane change efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the ego vehicle waits for environmental vehicles to yield based on turn light signals, then the lane change safety is improved, but the lane change efficiency deteriorates
Solution Approach 1:
The system performs preliminary actions by predicting the yielding behavior of environmental vehicles before executing the lane change. It calculates predicted offsets and determining whether environmental vehicles will yield in advance, allowing the ego vehicle to proactively plan its lane change trajectory rather than passively waiting, thus resolving the contradiction between safety and efficiency
Solution Approach 2:
The system changes the parameter of lane change decision-making from binary (wait or manual intervention) to continuous by introducing predicted offset values and yielding probabilities. This allows the ego vehicle to select optimal lane change parameters based on predicted environmental vehicle behavior, improving both safety through accurate prediction and efficiency through optimized timing
2Productivity
If manual intervention is used to trigger lane changes, then the lane change efficiency is improved, but the automation level deteriorates
Solution Approach 1:
The system implements self-service by enabling the autonomous vehicle to automatically predict environmental vehicle yielding behavior and determine optimal lane change timing without human intervention. The automated system serves itself by integrating prediction algorithms that assess whether environmental vehicles will yield, eliminating the need for manual trigger while maintaining high lane change efficiency
Solution Approach 2:
The system introduces feedback mechanisms by continuously monitoring environmental vehicle responses to turn light signals and using this information to refine predictions of yielding behavior. This feedback loop enables the automated system to learn from actual environmental vehicle reactions, improving the accuracy of automation decisions and maintaining high efficiency without manual intervention
Data Source
AI summary
Embodiments of this application disclose a vehicle-based data processing method performed by a computer device. The method includes: determining at least two predicted offsets of a first vehicle, a first traveling state of the first vehicle, and a second traveling state of a second vehicle; determining, according to the first traveling state and the second traveling state, first lane change payoffs of the predicted offsets when the second vehicle is in a yielding prediction state, and determining second lane change payoffs when the second vehicle is in a non-yielding prediction state; and determining a predicted yielding probability of the second vehicle, generating target lane change payoffs of the predicted offsets according to the predicted yielding probability and the first lane change payoffs and the second lane change payoffs of the predicted offsets, and determining a predicted offset having a maximum target lane change payoff as a target predicted offset.