UAV Obstacle Avoidance Using Multi-Sensor 3D Route Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional unmanned aerial vehicles (UAVs) face challenges in accurately recognizing and avoiding obstacles in complex environments, such as agricultural settings, due to their reliance on single signal acquisition methods, which can lead to safety hazards.

Innovation Solution

A multi-signal acquisition and route planning model that combines millimeter-wave radar, laser radar, binocular vision cameras, and ultrasonic transceivers to generate a three-dimensional environmental model and use a genetic algorithm for real-time obstacle avoidance, allowing the UAV to assess its capability to avoid obstacles and plan an appropriate route.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single signal acquisition means is used for obstacle detection, then the device complexity is reduced, but the measurement precision and reliability of obstacle recognition deteriorate in complex environments

Engineering Contradiction:
Improvesignal acquisition systemVSAvoidobstacle recognition accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines four different signal acquisition means (millimeter-wave radar, laser radar, binocular vision camera, and ultrasonic transceiver) into an integrated obstacle detection system. Each sensor type detects obstacles using different physical principles and is suitable for different scenarios, and their combined use comprehensively covers various obstacle types and environmental conditions, thereby improving measurement precision without excessively increasing device complexity through systematic integration.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent uses a composite sensing system that integrates multiple types of sensors with different detection capabilities. Similar to composite materials, this composite sensor system combines the advantages of each individual sensor type to achieve superior overall performance in obstacle detection, particularly in complex environments where single-sensor systems fail.

Inventive Principle:
Principle #40Composite materials

2Reliability

If multiple signal acquisition means are integrated for comprehensive obstacle detection, then the measurement precision and reliability improve, but the device complexity increases

Engineering Contradiction:
Improveobstacle avoidance safetyVSAvoidmulti-signal acquisition system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the obstacle detection task among four specialized sensors, each responsible for specific detection scenarios. The millimeter-wave radar handles moving obstacles, laser radar detects fine objects, binocular vision covers near distances, and ultrasonic transceivers provide directivity. This segmentation allows reliable obstacle detection while managing system complexity through functional division and specialized processing for each sensor type.

Inventive Principle:
Principle #1Segmentation

3Ease of operation

If conventional single-signal obstacle avoidance is used, then the ease of operation is maintained, but the adaptability to complex environments deteriorates

Engineering Contradiction:
Improveobstacle avoidance operationVSAvoidenvironmental adaptability
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal obstacle detection system that can adapt to various environmental conditions and obstacle types through multi-functional sensors. The system automatically selects and combines appropriate sensing methods based on the detection scenario, providing both ease of operation through automated selection and high adaptability to different environments including complex agricultural settings.

Inventive Principle:
Principle #6Universality (Multi-functionality)

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 enables accurate and efficient obstacle recognition and avoidance in complex environments, particularly at low altitudes, by integrating the strengths of different sensors for comprehensive data acquisition and real-time route planning, ensuring safe operation within a 0-12 m/s speed range.

Implementation Method 1

conducting signal acquisition processing on a first environmental area to obtain an initial millimeter-wave radar signal by utilizing millimeter-wave radar

Methodology Applied
Scientific EffectRadar: Radar

Implementation Method 2

conducting signal acquisition processing on a first environmental area to obtain an initial laser radar signal by utilizing laser radar

Methodology Applied
Scientific EffectLIDAR: LIDAR

Implementation Method 3

conducting signal acquisition processing on a first environmental area to obtain an initial image signal by utilizing a binocular vision camera

Methodology Applied
Scientific EffectBinocular vision: Parallax

Implementation Method 4

conducting signal acquisition processing on a first environmental area to obtain an initial ultrasonic signal by utilizing an ultrasonic transceiver

Methodology Applied
Scientific EffectUltrasonic detection: Ultrasound

Data Source

PatentUS11353893B1Obstacle avoiding method and apparatus for unmanned aerial vehicle based on multi-signal acquisition and route planning model
Publication Date: 2022.06.07 GUANGDONG POLYTECHNIC NORMAL UNIV
  • US11353893B1 patent drawing
  • US11353893B1 patent drawing

AI summary

Disclosed is an obstacle avoiding method and apparatus for an unmanned aerial vehicle based on a multi-signal acquisition and route planning model. The method comprises: conducting signal acquisition processing on a first environmental area to obtain an initial millimeter-wave radar signal, an initial laser radar signal, an initial image signal and an initial ultrasonic signal; generating an initial three-dimensional environmental model according to a preset dynamic environment real-time modeling method; acquiring a motion parameter and a body shape parameter of the unmanned aerial vehicle and inputting the parameters into an initial route planning model corresponding to the initial three-dimensional environmental model based on a genetic algorithm to process so as to obtain an output of the initial route planning model; judging whether the output is capable of avoiding an obstacle; if yes, generating an obstacle avoiding flight instruction to require the unmanned aerial vehicle to fly through the first environmental area.