UAV-Ground Vehicle Map Sharing for Distortion-Free Lane Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for mapping and object detection in movable objects, such as UAVs and ground vehicles, face challenges due to field of view and view angle limitations of sensors, leading to inaccurate data transformations and reduced reliability in applications like lane detection.

Innovation Solution

A system that shares sensor information between UAVs and ground vehicles, utilizing the UAV's ability to capture birds-eye view data directly, which is then transmitted to the ground vehicle for processing, thereby avoiding the need for perspective transformations and associated distortions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If perspective transformations are used to change the view angle of sensor data, then the field of view limitation is overcome, but processing time increases and distortions are introduced

Engineering Contradiction:

Improvefield of viewVSAvoidprocessing time

Core Design Contradiction:

Area of stationary objectVSLoss of time

Solution Approach 1:

Instead of transforming ground vehicle sensor data to simulate an aerial view, the system inverts the approach by directly using aerial vehicle sensor data to capture the desired birds-eye view perspective, eliminating the need for computationally intensive perspective transformations

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The aerial vehicle acts as an intermediary that captures sensor data from an elevated position and transmits it to the ground vehicle, providing the benefits of an expanded field of view without requiring the ground vehicle's sensors to perform complex transformations

Inventive Principle:

Principle #24Intermediary (Mediator)

2Area of stationary object

If perspective transformations are used to change the view angle of sensor data, then the field of view limitation is overcome, but data accuracy decreases due to distortions

Engineering Contradiction:

Improvefield of viewVSAvoiddata accuracy

Core Design Contradiction:

Area of stationary objectVSMeasurement precision

Solution Approach 1:

The system inverts the conventional approach by having the aerial vehicle directly capture the birds-eye view data needed for accurate measurement, rather than attempting to transform ground-level sensor data which inherently introduces geometric distortions

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The aerial vehicle serves as an intermediary sensor platform that collects data from the desired perspective (overhead birds-eye view), ensuring measurement accuracy by capturing data directly from the target viewpoint rather than transforming data from a different perspective

Inventive Principle:

Principle #24Intermediary (Mediator)

3Device complexity

If sensor data is captured from ground level, then device complexity is reduced, but field of view and detection capability are limited

Engineering Contradiction:

Improvesensor system complexityVSAvoidfield of view

Core Design Contradiction:

Device complexityVSArea of stationary object

Solution Approach 1:

The system merges the sensor capabilities of the aerial vehicle with the ground vehicle's processing and control systems, combining the aerial vehicle's elevated field of view advantage with the ground vehicle's computational resources to achieve enhanced detection without significantly increasing overall system complexity

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The aerial vehicle is equipped with multi-functional capabilities, serving both as a mobile sensor platform for capturing birds-eye view data and as a communication relay, while the ground vehicle utilizes the aerial data in addition to its own sensor data, maximizing the utility of each platform

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentEP3729402B1Techniques for sharing mapping data between an unmanned aerial vehicle and a ground vehicle

Publication Date: 2025.06.04 SZ DJI TECH CO LTD

Figure 1
Figure 2A
Figure 2B~2C

AI summary

A system for sharing sensor information between multiple vehicles includes an aerial vehicle (104) which includes a first computing device, first scanning sensor (118,124,126) and a ground vehicle (110) which includes a second computing device and second scanning sensor (130,132,134). The aerial vehicle (104) can use the first scanning sensor (118,124,126) to obtain first scanning data and transmit the first scanning data to the second computing device. The ground vehicle (110) can receive the first scanning data from the first computing device, obtain second scanning data from the second scanning sensor (130,132,134), identify an overlapping portion of the first scanning data and the second scanning data based on at least one reference object (202) in the scanning data, and execute a navigation control command based on one or more roadway objects identified in the overlapping portion of the first scanning data and the second scanning data. A method for sharing sensor information in an aerial vehicle, a non-transitory computer readable storage medium and a system for generating a map are disclosed.