Autonomous Vehicle Obstruction Maneuvering via Traffic Flow Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous driving systems face challenges in recognizing and responding to driving obstructions, such as traffic accidents or construction, due to insufficient information gathering, difficulty in deducing obstruction causes, and unpredictable driver responses, often requiring human intervention for navigation.

Innovation Solution

A system that utilizes a decision process framework to learn from surrounding vehicles and traffic flow, employing specialized detection and decision components to provide instructions for maneuvering around obstructions, comparing maneuvers with detours, and determining the most suitable route based on various factors for safe and efficient navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the autonomous driving system relies on a predictable set of observations, then the system can operate reliably under normal conditions, but the system fails to respond appropriately to unfamiliar situations such as driving obstructions

Engineering Contradiction:

Improvesystem reliability under normal conditionsVSAvoidsystem adaptability to unfamiliar situations

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic route planning that adapts to changing conditions by continuously monitoring traffic flow patterns and other vehicles' responses to obstructions. The system transitions from static, pre-planned routes to dynamic, real-time route adjustments based on observed traffic behavior, allowing the vehicle to adapt to unfamiliar situations while maintaining operational reliability.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system employs feedback mechanisms by observing and learning from the responses of other vehicles to obstructions. It collects data on how surrounding vehicles maneuver around obstacles and uses this feedback to inform its own routing decisions, enabling the system to adapt to unfamiliar situations through continuous learning from environmental feedback.

Inventive Principle:

Principle #23Feedback

2Loss of information

If the system gathers sufficient information about obstructions, then the system can make informed routing decisions, but the system requires more time and computational resources for analysis

Engineering Contradiction:

Improveinformation completeness about obstructionsVSAvoidtime for information gathering and analysis

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary route planning before encountering obstructions, preparing multiple potential routing options in advance. When obstructions are detected, the system can quickly evaluate pre-prepared alternatives rather than computing routes from scratch, reducing the time required for information gathering and analysis while maintaining comprehensive information about possible routes.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system gathers information selectively rather than comprehensively, focusing on key parameters such as traffic flow patterns and other vehicles' responses to obstructions. By concentrating on the most critical information needed for routing decisions rather than collecting all possible data, the system achieves sufficient information completeness with reduced time and computational resource requirements.

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If the system follows traditional routing algorithms, then the system can efficiently navigate predictable paths, but the system cannot handle unpredictable driver responses to obstructions

Engineering Contradiction:

Improvenavigation efficiency under predictable conditionsVSAvoidsystem ability to handle unpredictable situations

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system serves itself by learning from the behaviors of other vehicles in the environment. It observes how surrounding drivers respond to obstructions and uses this information to inform its own routing decisions, enabling the system to handle unpredictable driver responses without requiring complex pre-programmed rules for every possible scenario.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces traditional mechanical routing algorithms with an intelligence-based system that uses machine learning and pattern recognition. Instead of following rigid, pre-programmed routing rules, the system intelligently adapts its navigation by analyzing traffic flow patterns and learning from other vehicles' responses to obstructions, enabling it to handle unpredictable situations while maintaining navigation efficiency.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11113547B2Planning control in response to a driving obstruction during operation of an autonomous driving vehicle (ADV)

Publication Date: 2021.09.07 BAIDU USA LLC

AI summary

Described is a system for providing an autonomous driving control mechanism in response to a driving obstruction. The system includes a framework for providing a decision process that may learn from surrounding vehicles and traffic flow to determine a suitable responsive action. The system may observe other vehicles and determine a trajectory for the vehicle to follow. The system may rely on a specialized blocking detection and decision components that may provide a set of instructions or rules in order to maneuver around the obstruction. In addition, the system may compare the maneuver with a detour and determine the most suitable route for the vehicle based on an analysis of several factors. Accordingly, the system may continue to provide safe and efficient autonomous control even when encountering a driving obstruction.