Mapping Through Dynamic Object Inferences

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current mapping technologies struggle to provide lane-level granularity in road mapping due to the lack of fine-grained information about road features like lane configurations, sidewalks, and crosswalks, often relying on manual annotation or GPS data that is inaccurate and inefficient, especially in environments with obstructions.

Innovation Solution

A vehicle-equipped mapping system using onboard sensors like LiDAR to detect and track dynamic objects, such as vehicles and pedestrians, to infer lane-level configurations and features, allowing for accurate and efficient mapping of road environments in a single pass, rather than requiring multiple passes along different paths.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If GPS information is used to determine lane-level paths, then mapping coverage can be achieved, but accuracy deteriorates due to interference from buildings, tunnels, and other obstructions

Engineering Contradiction:

Improvemapping coverageVSAvoidlocation accuracy

Core Design Contradiction:

Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent introduces dynamic objects (vehicles, pedestrians, cyclists) as intermediaries between the mapping system and the road environment. Instead of directly measuring road features with GPS, the system tracks the movements of these dynamic objects to infer lane-level paths and road configurations, thereby overcoming GPS signal blockage from buildings and tunnels

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the GPS-based mechanical positioning system with an optical/sensor-based tracking system. By using cameras and sensors to detect and track dynamic objects, the system substitutes the GPS measurement mechanism with a visual observation mechanism that is not affected by signal blockage

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If multiple separate passes are made along different paths to acquire complete road representation, then comprehensive mapping is achieved, but productivity deteriorates due to the multitude of required passes

Engineering Contradiction:

Improvecompleteness of road representationVSAvoidmapping efficiency

Core Design Contradiction:

Loss of informationVSProductivity

Solution Approach 1:

The patent merges the mapping function with the normal operation of dynamic objects in the environment. Instead of dedicating separate passes for mapping, the system combines mapping data collection with the natural movements of vehicles and pedestrians, allowing comprehensive road representation to be built incrementally during regular traffic flow

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent implements continuous mapping through ongoing tracking of dynamic objects as they naturally move through the environment. Rather than discrete mapping passes, the system continuously accumulates path information from dynamic objects, enabling progressive construction of complete road representations without interrupting normal traffic

Inventive Principle:

Principle #20Continuity of useful action

3Measurement precision

If manual annotation is used to encode lane and granular features, then mapping precision is improved, but productivity deteriorates due to the labor-intensive process

Engineering Contradiction:

Improvelane-level detail accuracyVSAvoidmapping speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent enables the mapping system to automatically extract lane-level information from the tracked paths of dynamic objects without requiring manual annotation. The system self-serve by using the natural movement patterns of vehicles and pedestrians to automatically define lanes, turn lanes, and road features, eliminating the need for human annotators while maintaining high precision

Inventive Principle:

Principle #25Self-service

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances mapping efficiency and accuracy by leveraging sensor data to generate detailed, lane-level maps that improve autonomous driving and obstacle avoidance systems, while reducing the reliance on manual processes and improving change detection in dynamic environments.

Implementation Method 1

The mapping system uses the onboard sensors (e.g., LiDAR sensor) to detect and track dynamic objects in the surrounding environment

Methodology Applied

Scientific EffectTime of Flight: Time of Flight

Data Source

PatentUS10753750B2System and method for mapping through inferences of observed objects

Publication Date: 2020.08.25 TOYOTA JIDOSHA KK

AI summary

System, methods, and other embodiments described herein relate to improving mapping of a surrounding environment by a mapping vehicle. In one embodiment, a method includes identifying dynamic objects within the surrounding environment that are proximate to the mapping vehicle from sensor data of at least one sensor of the mapping vehicle. The dynamic objects are trackable objects that are moving within the surrounding environment. The method includes generating paths of the dynamic objects through the surrounding environment relative to the mapping vehicle according to separate observations of the dynamic objects embodied within the sensor data. The method includes producing a map of the surrounding environment from the paths.