Autonomous Vehicle Path Control Without HD Map Dependence

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing automated driving systems (ADS) rely heavily on high-definition (HD) maps, which limit their ability to predict the position and attitude of autonomous vehicles in environments without clear lanes or newly drawn lanes, making it difficult to generate accurate driving paths and control steering angles.

Innovation Solution

A system and method using artificial neural networks to generate and control driving paths based on sensing data from autonomous vehicles, where driving intention information and target speed are used to generate multiple paths, evaluate risk, and determine steering angles, allowing for path control without relying on HD maps.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If HD maps are used for path generation and vehicle position prediction, then driving path accuracy is improved in environments with clear lanes, but the system fails to operate in environments without clear lanes or newly drawn lanes

Engineering Contradiction:

Improvevehicle position prediction accuracyVSAvoidenvironmental adaptability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent introduces an artificial neural network as an intermediary between sensor data and path generation, replacing the direct dependency on HD maps. The neural network processes sensor data to predict vehicle position and generate paths, acting as a mediator that can operate with or without HD map information, thus resolving the contradiction between measurement precision and environmental adaptability

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical/HD-map-dependent path generation system with an artificial intelligence-based system. Instead of relying on pre-defined map data structures, the system uses neural networks to learn and adapt to various road environments, substituting rigid map-based mechanics with flexible AI-based processing that can handle diverse conditions

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If multiple driving paths are generated using artificial neural networks, then path options matching driving intention are improved, but computational complexity increases

Engineering Contradiction:

Improvedriving intention matching capabilityVSAvoidcomputational complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-training the artificial neural networks with extensive driving data before deployment. The networks learn path generation patterns and risk evaluation criteria in advance, so that during actual operation, they can quickly generate multiple candidate paths and evaluate them without requiring complex real-time computations, thus balancing adaptability with computational feasibility

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11866067B2System and method for generating and controlling driving paths in autonomous vehicle

Publication Date: 2024.01.09 ELECTRONICS & TELECOMM RES INST

AI summary

Provided is a method of generating and controlling a driving path for an autonomous vehicle, the method including generating a driving path that matches a driving intention on the basis of sensing data acquired from a sensing module of the autonomous vehicle, determining steering angle information corresponding to the generated driving path, and controlling a steering angle of the autonomous vehicle.