Underwater Depth Perception Sensors With Onboard 3D Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing underwater depth perception technologies rely heavily on remote computing, leading to delays and insufficient detail in real-time feedback, and often overwhelm onboard computing resources, limiting effective navigation and collision avoidance in underwater environments.
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 provide real-time depth perception and navigation capabilities, using techniques such as triangulation and image processing to generate high-resolution depth maps and 3D point clouds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If laser-based sensors, sonar-based sensors, and navigation sensors are used for underwater depth perception, then measurement precision is improved, but device complexity increases and onboard computing resources are overwhelmed
Solution Approach 1:
The patent combines multiple sensor types (image sensor, complementary sensor, inertial measurement unit, and depth sensor) into an integrated sensor system that processes data collectively. This merging approach consolidates the functionality of separate laser-based sensors, sonar-based sensors, and navigation sensors into a unified system that achieves high measurement precision while managing device complexity through integrated data processing.
Solution Approach 2:
The sensor system is designed to perform multiple functions simultaneously: the image sensor captures visual data, the complementary sensor provides additional measurement data, the inertial measurement unit tracks motion, and the depth sensor measures distance. This multi-functional system replaces the need for separate specialized sensors, reducing overall system complexity while maintaining high depth perception precision through coordinated operation of all sensors.
2Device complexity
If remote computing is used for processing depth perception data, then device complexity is reduced, but response time increases and real-time feedback is insufficient
Solution Approach 1:
The computing system is segmented into onboard processing units that handle critical real-time depth perception data locally, and remote computing resources that handle less time-sensitive tasks. This segmentation allows the system to process navigation-critical data immediately on the autonomous underwater vehicle while reducing overall computational complexity by offloading non-critical processing to remote systems, thereby minimizing response time for essential functions.
Solution Approach 2:
The patent introduces an onboard computing system that acts as an intermediary between the sensors and remote computing resources. This intermediary processes sensor data locally to generate real-time depth perception feedback, then selectively transmits processed information to remote systems. The intermediary ensures that time-critical processing occurs locally while still utilizing remote computing capabilities for supplementary tasks, thus reducing computational delay for real-time operations.
3Measurement precision
If multiple sensors are used for detailed depth perception, then measurement precision is improved, but onboard computing resources are overwhelmed
Solution Approach 1:
The system processes sensor data at different levels of detail based on operational requirements. For routine navigation, partial processing of sensor data is performed to generate sufficient depth information without full computational analysis. For critical obstacle detection or detailed mapping tasks, the system activates full processing capacity. This partial action approach maintains high measurement precision when needed while reducing computational energy consumption during normal operations by processing only the necessary portion of sensor data.
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
Enables real-time, high-resolution depth perception and navigation, allowing for precise avoidance of underwater obstacles and enhanced underwater robotics applications by processing data onboard, reducing reliance on remote computing and improving computational efficiency.
Implementation Method 1
provides underwater depth perception based on data captured by the plurality of image sensors and by measuring relative positions of objects in images captured by the image sensors
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.