Autonomous Vehicle Trajectory Planning for Early Lane Change Intent

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles struggle to accurately predict the intent of surrounding vehicles when they intend to change lanes, leading to potentially unsafe and unnatural driving maneuvers due to uncertainty and data noise in perception systems.

Innovation Solution

An autonomous vehicle system uses sensors and machine learning models to monitor the lateral position and velocity of nearby vehicles, predicting their trajectory and likelihood of collision, and adjusts its path to avoid potential collisions by determining alternative trajectories.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the autonomous vehicle uses basic perception systems to detect surrounding vehicles, then the system complexity is low, but the measurement precision of lateral position and velocity is insufficient leading to inaccurate intent prediction

Engineering Contradiction:
Improvelateral position and velocity measurement precisionVSAvoidperception system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by continuously monitoring and storing lateral position and velocity data before a lane change occurs. This historical data is used to calculate lateral acceleration and predict future trajectories, enabling accurate intent prediction before the actual lane change happens, thus improving measurement precision without requiring more complex hardware.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If the autonomous vehicle monitors and predicts trajectories of all surrounding vehicles, then the safety is improved, but the computational complexity and processing time increase

Engineering Contradiction:
Improvecollision avoidance reliabilityVSAvoidtrajectory prediction system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system applies local quality by focusing computational resources on vehicles that exhibit lane change intent characteristics (specific lateral position and velocity patterns) rather than uniformly processing all surrounding vehicles. This selective approach maintains high collision avoidance reliability while reducing overall computational complexity by identifying and prioritizing only relevant targets.

Inventive Principle:
Principle #3Local quality

3Speed

If the autonomous vehicle reacts immediately to detected lane change attempts, then the response time is reduced, but the driving maneuvers become unnatural and uncomfortable

Engineering Contradiction:
Improveresponse speedVSAvoiddriving comfort
Core Design Contradiction:
SpeedVSEase of operation

Solution Approach 1:

The system performs preliminary prediction of lane change intent using lateral acceleration calculations and trajectory projection before the actual lane change occurs. This allows the autonomous vehicle to prepare smooth, gradual trajectory adjustments in advance, maintaining fast response while ensuring natural and comfortable driving maneuvers by avoiding sudden reactions.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12447951B2Traffic object intent estimation
Publication Date: 2025.10.21 TORC ROBOTICS INC
  • US12447951B2 patent drawing
  • US12447951B2 patent drawing
  • US12447951B2 patent drawing

AI summary

A method comprises periodically monitoring, by a processor, lateral position and velocity of vehicle within a predetermined distance from an autonomous vehicle, the vehicle moving in a direction having at least one common attribute with the autonomous vehicle; executing, by the processor, a computer model using the monitored lateral position and velocity of the vehicle, to predict whether a trajectory for the vehicle; and when a current trajectory of the autonomous has a likelihood of collision with the predicted trajectory of the vehicle that satisfies a threshold, determining, by the processor, an alternative trajectory for the autonomous vehicle.