Vehicle Localization via Dynamic Object Reference Sharing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing localization methods for moving objects, such as vehicles and pedestrians, in urban environments face challenges due to reliance on satellite-based systems and pre-constructed maps, which can be unreliable in areas with signal obstruction and lack of map updates, failing to provide the high accuracy needed for autonomous driving applications.

Innovation Solution

A method that improves localization accuracy by leveraging vehicle-to-vehicle communication to exchange and refine localization estimates based on dynamic objects' positions relative to a global reference frame, allowing vehicles to estimate and share localization packets with each other anonymously, without relying on absolute location sharing or direct perception of other vehicles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If satellite-based localization methods are used, then localization coverage is improved, but localization accuracy deteriorates in urban environments with signal obstruction

Engineering Contradiction:

Improvelocalization coverageVSAvoidlocalization accuracy

Core Design Contradiction:

Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent introduces dynamic objects (pedestrians, cyclists, animals) as intermediary reference points for localization. Instead of relying directly on satellite signals or static landmarks, the system uses moving objects that are detected by multiple sensors to establish relative position relationships, thereby achieving accurate localization in urban environments where traditional methods fail

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables vehicles to perform multiple functions: detecting dynamic objects, estimating their trajectories, calculating relative positions, and exchanging localization information. This multi-functional approach allows a single system to address both detection and localization needs, improving accuracy without requiring separate specialized infrastructure

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If map-based localization methods are used, then localization accuracy is improved when maps are available, but adaptability deteriorates in areas without pre-constructed maps

Engineering Contradiction:

Improvelocalization accuracyVSAvoidenvironmental adaptability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent transitions from static map-based references to dynamic object-based references. By using moving objects whose positions are continuously tracked and updated, the system adapts to changing environments in real-time, whether pre-constructed maps exist or not, thereby achieving both accuracy and environmental versatility

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs preliminary detection and tracking of dynamic objects before using them for localization. By continuously monitoring and predicting object trajectories in advance, the system prepares reference data that can be immediately used for accurate positioning when needed, regardless of map availability

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If base station communication is used, then localization accuracy is improved when base stations are available, but device complexity increases due to communication requirements

Engineering Contradiction:

Improvelocalization accuracyVSAvoidcommunication infrastructure complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system enables vehicles to perform localization using their own sensor data and the data of other detected vehicles. By self-determining positions through relative measurements of dynamic objects rather than relying on external base station infrastructure, the system reduces communication complexity while maintaining accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback loops where vehicles continuously exchange localization information and refine their position estimates based on received data. This iterative refinement process improves accuracy without requiring complex centralized communication infrastructure, as each vehicle independently processes and updates its localization based on feedback from peers

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20230166759A1Systems and methods for improving localization accuracy by sharing dynamic object localization information

Publication Date: 2023.06.01 TOYOTA RESEARCH INSTITUTE INC

AI summary

Systems and methods are provided for improving a localization estimate of a vehicle by leveraging localization estimates of surrounding dynamic objects from surrounding vehicles. A vehicle may estimate its own location relative to a global reference frame. The vehicle may identify nearby dynamic objects. The vehicle may estimate the location of the nearby dynamic objects. The vehicle and nearby vehicles may generate and exchange localization packets containing information about the dynamic objects and the location estimates for the dynamic objects. The vehicle may refine its localization estimate based on received localization packets.