Quadratic Programming Path Planning for Autonomous Vehicle Pull-Over

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous driving vehicles face challenges in precisely pulling over to the right side of a lane with a small distance to the boundary and being parallel to it, which is crucial for passenger access.

Innovation Solution

A method using quadratic programming to plan a path with a first segment generated from the start point to a transition point and a second segment based on the lane boundary shape, ensuring the vehicle is controlled to pull over accurately and efficiently.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional path planning methods are used for pulling over, then the vehicle can reach the destination, but the distance accuracy to the lane boundary and parallelism are insufficient

Engineering Contradiction:

Improvedistance accuracy to lane boundaryVSAvoidpulling over precision

Core Design Contradiction:

Measurement precisionVSManufacturing precision

Solution Approach 1:

The patent transforms the path planning problem into a quadratic programming optimization problem by defining specific parameters: minimizing the distance to the lane boundary while maintaining parallelism constraints. The cost function includes terms for distance minimization and orientation alignment, allowing precise control of the vehicle's final position and attitude through parameter optimization.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces traditional geometric or heuristic path planning methods with a mathematical optimization approach (quadratic programming). Instead of using complex mechanical control adjustments during the pulling over process, the system uses computational optimization to directly calculate the optimal path parameters that satisfy both distance and parallelism requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If the vehicle pulls over closer to the lane boundary, then passenger access convenience is improved, but the risk of collision with the boundary increases

Engineering Contradiction:

Improvepassenger access convenienceVSAvoidcollision risk

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent optimizes the distance parameter between the vehicle and lane boundary through quadratic programming. The cost function minimizes this distance to improve passenger access, while constraint conditions ensure the distance remains within safe limits, thus balancing convenience and collision risk.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses real-time feedback from the optimization process to adjust the path parameters. By continuously evaluating the cost function and constraints during path planning, the system adapts the vehicle's position to achieve the optimal balance between closeness to the boundary (for passenger access) and safety margins (to prevent collision).

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11529969B2Pull over method based on quadratic programming for path planning

Publication Date: 2022.12.20 BAIDU USA LLC

AI summary

In response to a request to pull over an ADV at a destination point at a side of a lane, a path including a first segment, a second segment and a transition point is planned. The transition point is determined based on at least one of a distance to the destination point or a predetermined distance to a boundary of the side of the lane. The first segment from a start point to the transition point is generated by using a quadratic programming (QP) operation. The second segment from the transition point to the destination is generated based on a shape of the boundary. The ADV is controlled to pull over to the destination point according to the planned path.