Cloud-Based Object Recognition for Robots
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud computing systems lack the ability to efficiently integrate and utilize robotic devices for tasks such as object recognition, mapping, and navigation, as they require onboard knowledge bases that can be limited in capacity and outdated, hindering collaborative and adaptive functionalities.
Innovation Solution
Implementing a cloud-based system where robots can interact with a network of computers to access and share data, using contextual and situational information to identify objects and perform tasks, allowing for external data storage and processing, thereby enhancing object recognition, mapping, and navigation capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If robots use onboard knowledge bases for object recognition and navigation, then they can perform tasks autonomously, but the knowledge bases become limited in capacity and outdated
Solution Approach 1:
The patent extracts the knowledge base from the robot and places it in the cloud. Robots send images and data to cloud servers for processing, which return object identifications and navigation instructions. This allows robots to access vast, up-to-date knowledge without storing it locally, resolving the contradiction between autonomous operation and limited onboard storage capacity.
Solution Approach 2:
The cloud server acts as an intermediary between robots and the vast repository of knowledge. Instead of robots maintaining large local databases, they communicate with the cloud intermediary that processes images and provides responses, enabling extended knowledge capacity while maintaining robot autonomy.
2Productivity
If robots maintain extensive onboard storage for data and knowledge, then they can perform complex tasks independently, but device complexity and maintenance requirements increase
Solution Approach 1:
The patent removes data storage and knowledge processing functions from the robot and relocates them to cloud infrastructure. Robots only retain minimal local storage for basic operations and communication, significantly reducing device complexity while maintaining high productivity through cloud-based processing.
Solution Approach 2:
The cloud server provides universal processing capabilities for multiple robots simultaneously. Instead of each robot maintaining dedicated storage and processing hardware, the system uses a shared cloud infrastructure that serves all robots, reducing individual device complexity while preserving task execution capability.
3Reliability
If robots use static onboard knowledge bases, then they can operate autonomously, but the knowledge becomes outdated and less accurate
Solution Approach 1:
The cloud-based system continuously receives feedback from robots about their environment and task performance. This feedback loop allows the cloud knowledge base to be updated with new information and corrected errors, ensuring high accuracy and currency of knowledge while robots maintain autonomous operation using the latest data.
Data Source
AI summary
Examples disclose systems and methods for recognizing objects. A method may be executable to receive a query from a robot. The query may include identification data associated with an object and contextual data associated with the object. The query may also include situational data. The method may also be executable to identify the object based at least in part on the data in the query received from the robot. Further, the method may be executable to send data associated with the identified object to the robot in response to the query.