Autonomous Intersection Speed Planning Using Predicted Vehicle Tracks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing autonomous driving technologies struggle to accurately predict vehicle movements and determine right-of-way rules at complex intersections, leading to unsafe and inefficient passage through unprotected intersections.

Innovation Solution

An autonomous driving method that determines a traveling track set for a vehicle based on predicted tracks of surrounding vehicles, calculates intersection times, and adjusts speed to ensure safe and efficient passage by considering right-of-way rules and sensor data without real-time vehicle communication.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If autonomous driving technology uses conventional prediction methods at intersections, then the system complexity remains low, but the accuracy of predicting vehicle movement tracks and determining right-of-way rules deteriorates

Engineering Contradiction:
Improveprediction accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the intersection area into multiple detection zones and divides the prediction task into separate sub-tasks for different vehicle groups. By processing vehicle tracks in segments rather than as a whole, the system achieves more accurate predictions while keeping computational complexity manageable through modular processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-establishing right-of-way rules and prediction models before vehicles reach the intersection. Vehicle movement tracks are predicted in advance using historical data and conventional methods, allowing the system to prepare multiple candidate tracks and select the optimal one when the vehicle approaches, thereby improving accuracy without requiring complex real-time processing.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If autonomous driving technology relies on real-time communication between vehicles, then the accuracy of tracking vehicle movements improves, but the device complexity and communication requirements increase

Engineering Contradiction:
Improvetracking accuracyVSAvoidcommunication system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements self-service by enabling each autonomous vehicle to independently predict and track other vehicles' movements using its own sensors and processing capabilities. Instead of relying on centralized communication infrastructure, each vehicle serves itself by autonomously determining right-of-way rules and predicting tracks of surrounding vehicles, thereby achieving reliable tracking without increasing communication system complexity.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system introduces an intermediary layer of prediction models and right-of-way rule databases that mediate between raw sensor data and vehicle control decisions. These intermediaries process and interpret vehicle movement patterns, allowing accurate tracking without requiring direct real-time communication between all vehicles, thus maintaining simplicity while improving reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Speed

If autonomous driving technology processes complex intersection scenarios in real-time, then the response speed improves, but the computational complexity and processing time increase

Engineering Contradiction:
Improveresponse speedVSAvoidcomputational complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by pre-calculating and storing right-of-way rules, typical vehicle trajectories, and intersection geometry data before vehicles arrive. When a vehicle approaches an intersection, the system quickly retrieves pre-prepared information and applies it to the current situation, achieving fast response without requiring complex real-time computations for every decision.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent segments the computational task into distinct modules: detection of vehicles in different zones, prediction of each vehicle's track based on its group, determination of right-of-way rules for each pair of vehicles, and final speed adjustment. This segmentation allows parallel processing of multiple vehicles simultaneously, improving response speed while managing computational complexity through modular architecture.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4086875B1Self-driving method and related device
Publication Date: 2025.07.23 YINWANG INTELLIGENT TECHNOLOGIES CO LTD
  • EP4086875B1 patent drawingFigure 1A
  • EP4086875B1 patent drawingFigure 1B
  • EP4086875B1 patent drawingFigure 2A

AI summary

An autonomous driving method and a related device are provided. The autonomous driving method includes: determining, based on a first traveling track currently planned by a first vehicle, a traveling track set corresponding to the first traveling track; determining an intersection track segment on each second traveling track in the traveling track set; separately determining, based on current speeds and current locations that correspond to N second vehicles, intersection times at which the N second vehicles arrive at the intersection track segment; and determining a speed of the first vehicle based on the intersection track segment on each second traveling track in the traveling track set and the corresponding intersection time. This can effectively ensure that an autonomous vehicle can safely and efficiently pass through an intersection.