Underwater Depth Perception with Onboard Multi-Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing underwater depth perception technologies rely heavily on remote computing, leading to delays and insufficient real-time feedback, and existing sensors like sonar and LiDAR provide limited detail and specificity, overwhelming onboard computing resources.
Innovation Solution
Implementing systems with multiple image sensors or a combination of an image sensor and a complementary sensor, along with onboard computing systems, to enable real-time depth perception and navigation by processing data locally.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sonar or laser-based sensors are used for underwater depth perception, then real-time feedback for navigation is provided, but the feedback lacks detail and specificity and overwhelms onboard computing resources
Solution Approach 1:
The patent extracts only the essential depth information needed for navigation from the overwhelming sensor data, processing only relevant features and distances rather than analyzing complete sonar or laser point clouds, thereby reducing computing resource load while maintaining adequate depth perception capability
Solution Approach 2:
The system uses multiple sensors including sonar, laser, and cameras, allowing some sensors to provide redundant or overlapping information, which ensures adequate depth perception coverage while distributing the processing load across multiple simpler processing channels rather than one complex processor
2Power
If remote computing is used for depth perception processing, then computing resources are available, but delays occur that limit real-time depth perception capability
Solution Approach 1:
The system pre-loads depth perception algorithms and processing routines into onboard memory before deployment, and pre-configures sensor synchronization protocols, so that when depth perception is needed, processing can begin immediately without waiting for remote system initialization or configuration
Solution Approach 2:
The patent introduces an onboard edge computing unit that acts as an intermediary between the sensors and remote computing systems, performing initial depth perception processing locally to provide immediate feedback, then selectively transmitting only essential data to remote systems for further analysis, thereby eliminating delays while maintaining access to advanced computing capabilities
3Adaptability or versatility
If multiple sensor types are used for comprehensive underwater observation, then depth perception capability is improved, but the system complexity and resource requirements increase
Solution Approach 1:
The patent designs sensor mounts and processing systems that can accommodate multiple sensor types (sonar, laser, cameras) using common mounting interfaces, power supply systems, and data processing pipelines, allowing the system to achieve comprehensive underwater observation capability while managing complexity through standardized multi-functional architecture
Solution Approach 2:
The system combines multiple sensor types into an integrated depth perception system where sonar, laser, and camera data are processed together through unified algorithms, merging their individual capabilities into a single comprehensive depth perception function rather than operating them as separate independent systems
Data Source
AI summary
Systems described herein use either multiple image sensors or one image sensor and a complementary sensor to provide underwater depth perception. The systems include a computing system that provides the underwater depth perception based on data sensed by the multiple image sensors or the one image sensor and the complementary sensor. The systems can include a submersible device (such as a submersible mobile machine) that includes a holder configured to hold the one image sensor. The holder can be configured to hold the computing system in addition to the one image sensor. And, in some embodiments, the holder is configured to hold the complementary sensor in addition to the computing system and the one image sensor. Alternatively, in some embodiments, the holder is configured to hold the multiple image sensors. And, the holder can be configured to hold the computing system in addition to the multiple image sensors.