Spiral Path Three-Point Turn Planning for Autonomous Vehicles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

There is a lack of efficient methods for planning and controlling autonomous driving vehicles to perform a three-point turn, which is necessary for U-turns in narrow roads where continuous U-turns are not possible without stopping and reversing.

Innovation Solution

A computer-implemented method that generates a forward turning path using a first spiral function based on the maximum forward curvature change rate and a backward turning path using a second spiral function based on the maximum backward curvature change rate, initiating the backward path from the end point of the forward path, and combining these to create a three-point turn path for the autonomous driving vehicle.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional three-point turn planning methods are used, then the vehicle can perform U-turns on narrow roads, but the path planning is complicated and lacks efficiency

Engineering Contradiction:
Improvethree-point turn execution efficiencyVSAvoidpath planning complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The three-point turn path is segmented into three distinct phases: forward turning path, backward turning path, and final forward movement. Each phase is planned independently using appropriate spiral functions, simplifying the overall complex maneuver into manageable segments that can be executed sequentially

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Spiral functions are used to generate smooth curved paths for both forward and backward turning phases. The spiral curvature ensures continuous and differentiable path transitions, avoiding abrupt direction changes while maintaining planning simplicity through mathematical parameterization

Inventive Principle:
Principle #14Spheroidality (Curvature)

2Manufacturing precision

If spiral functions with maximum curvature change rates are used, then the turning paths are precise and smooth, but the computational complexity increases

Engineering Contradiction:
Improvepath precisionVSAvoidcomputational complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The spiral functions are parameterized using maximum curvature change rates as key parameters. By adjusting these parameters, the path precision can be controlled while maintaining computational efficiency through closed-form mathematical solutions rather than iterative optimization

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11267471B2Spiral path based three-point turn planning for autonomous driving vehicles
Publication Date: 2022.03.08 BAIDU USA LLC
  • US11267471B2 patent drawing
  • US11267471B2 patent drawing
  • US11267471B2 patent drawing

AI summary

In one embodiment, in response to a request to make a three-point turn for an autonomous driving vehicle (ADV), a forward turning path is generated using a first spiral function based on a maximum forward curvature change rate. A backward turning path is generated using a second spiral function based on a maximum backward curvature change rate. The forward and backward curvature change rates may be determined based on the maximum forward and backward turning angles associated with the ADV, which may be specified as a part of vehicle specification or vehicle design of the ADV. The backward turning path is initiated from an end point of the forward turning path. A three-point turn path is then generated based on the forward turning path and the backward turning path. The ADV is then driven according to the three-point turn path by issuing one or more proper control commands.