Cloud SLAM for Real-Time Robot Localization and Map Patching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots face challenges in performing accurate simultaneous localization and mapping (SLAM) due to the high computational demands of processing high-precision spatial information, requiring advanced computing power and efficient data processing to navigate and map their environments effectively.
Innovation Solution
A method involving a robot and a cloud server that collaboratively perform SLAM, where the robot transmits sensor data to the cloud server for processing, allowing for real-time localization and map generation using LiDAR and camera sensors, with the cloud server handling high-capacity computations to improve map quality and localization accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the robot processes high-precision spatial information locally, then the localization accuracy is improved, but the computing power requirement and processing time increase
Solution Approach 1:
The patent introduces a cloud server as an intermediary to handle the heavy computational burden of processing high-precision spatial information from LiDAR and camera sensors. The robot captures sensor data and transmits it to the cloud server, which performs the computationally intensive SLAM processing and returns localization results, thereby improving localization accuracy without requiring the robot to have high computing power onboard
Solution Approach 2:
The patent transitions the computational processing from the robot's local environment to a remote cloud environment, effectively moving the processing dimension from edge computing to cloud computing. This dimensional shift allows high-precision spatial information to be processed with superior computational resources while the robot maintains mobility and operational independence
2Manufacturing precision
If the robot uses high-precision spatial information, then the mapping quality is improved, but the data processing time increases
Solution Approach 1:
The cloud server acts as a mediator that receives high-precision spatial data from the robot's sensors, processes it using powerful computational resources, and generates high-quality maps. This approach improves mapping quality by enabling thorough processing of detailed spatial information without causing time delays at the robot's end, as the processing occurs in parallel in the cloud environment
Solution Approach 2:
The system performs preliminary data transmission and processing preparation by sending sensor data to the cloud server in advance, allowing the computationally intensive mapping operations to begin before the robot completes its data collection cycle. This preliminary action enables high-quality map generation without creating bottlenecks in the robot's operational timeline
3Productivity
If the robot transmits sensor data to the cloud server, then the processing capability is improved, but the communication dependency increases
Solution Approach 1:
The SLAM system is segmented into two distinct functional components: the robot's onboard sensors and processors that handle data acquisition and preliminary processing, and the cloud server that handles intensive computational processing. This segmentation allows the system to leverage cloud computing power while maintaining the robot's operational autonomy and reducing communication dependency through localized preliminary processing
Data Source
AI summary
Provided are a method of performing cloud simultaneous localization and mapping (SLAM), and a robot and a cloud server for performing the same, and a robot for performing cloud SLAM in real time includes a first sensor configured to acquire sensor data necessary to perform the SLAM, a map storage unit configured to store a map synchronized with a cloud server, a communication unit configured to transmit the sensor data, a feature, or a last frame to the cloud server and receive a local map patch or a global pose from the cloud server, and a control unit configured to generate the sensor data, the feature extracted from the sensor data, or the last frame and control movement of the robot using the local map patch or the global pose received from the cloud server.