Autonomous Vehicle Park-and-Go Mode Switching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous driving vehicles face challenges in transitioning from a parked position to a driving lane due to obstacles and non-aligned parking spots, which require innovative navigation strategies to ensure safe and efficient movement.

Innovation Solution

The implementation of an open-space mode and on-lane mode system, where the vehicle can generate open-space trajectories for maneuvering around obstacles and aligning with the driving lane, and switch to on-lane mode once criteria such as distance and heading thresholds are met, utilizing sensors and planning modules for real-time decision-making.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the ADV uses a standard lane-following mode to transition from parked position to driving lane, then the vehicle can operate with simple control logic, but it cannot handle obstacles or non-aligned parking spots effectively

Engineering Contradiction:

Improveability to handle obstacles and non-aligned parking spotsVSAvoidcontrol system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The control system is segmented into two distinct modes: open-space planning mode for navigating from parked position to driving lane, and on-lane planning mode for following the driving lane. This segmentation allows each mode to be optimized independently, handling different scenarios with appropriate complexity levels.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically switches between open-space planning mode and on-lane planning mode based on the vehicle's current state and environmental conditions. This dynamic mode switching enables the vehicle to adapt its control strategy in real-time, improving versatility without permanently increasing system complexity.

Inventive Principle:

Principle #15Dynamics

2Reliability

If the ADV generates open-space trajectories to navigate around obstacles and align with driving lane, then the vehicle can safely transition from various parking positions, but it requires complex real-time decision-making and trajectory generation

Engineering Contradiction:

Improvesafe transition from parked positionVSAvoidtrajectory generation complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The open-space planning module pre-generates a trajectory from the parked position to the driving lane before the vehicle begins movement. This preliminary trajectory generation allows the vehicle to follow a pre-computed safe path, reducing the need for complex real-time decision-making during execution.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The open-space planning module acts as an intermediary between the high-level navigation goal and the low-level vehicle control. It translates the goal of reaching the driving lane into a detailed trajectory that accounts for obstacles and parking position, simplifying the control task.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If the ADV switches between open-space mode and on-lane mode based on distance and heading thresholds, then the vehicle can efficiently navigate to driving lane, but it requires continuous monitoring and mode switching logic

Engineering Contradiction:

Improvenavigation efficiencyVSAvoidmode switching logic complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system continuously monitors the vehicle's distance to the driving lane and heading angle, using this feedback to determine when to switch between open-space mode and on-lane mode. This feedback mechanism enables automatic mode switching based on simple threshold comparisons, improving efficiency without excessive complexity.

Inventive Principle:

Principle #23Feedback

4Extent of automation

If the ADV uses minimal human interaction for autonomous navigation, then the vehicle can operate driverless, but it must handle all transition scenarios autonomously without driver assistance

Engineering Contradiction:

Improveautonomous operation capabilityVSAvoidautonomous navigation complexity

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The autonomous navigation system is segmented into distinct planning modules (open-space planning and on-lane planning) that handle different phases of the navigation task. This segmentation reduces the complexity of autonomous operation by breaking it down into manageable, specialized components.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11577758B2Autonomous vehicle park-and-go scenario design

Publication Date: 2023.02.14 BAIDU USA LLC

AI summary

In one embodiment, when an autonomous driving vehicle (ADV) is parked, the ADV can determine, based on criteria, whether to operate in an open-space mode or an on-lane mode. The criteria can include whether the ADV is within a threshold distance and threshold heading relative to a vehicle lane. If the criteria are not satisfied, then the ADV can enter the open-space mode. While in the open-space mode, the ADV can maneuver it is within the threshold distance and the threshold heading relative to the vehicle lane. In response to the criteria being satisfied, the ADV can enter and operate in the on-lane mode for the ADV to resume along the vehicle lane.