Self-Moving Robot Recognition Using Edge-Cloud Image Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-moving devices face inaccuracies in recognizing their environment due to limitations in recognition technology, leading to potential misactions in complex real-world scenarios.
Innovation Solution
An automatic working system that includes a self-moving device equipped with an image detection module and a server with a second recognition module, utilizing deep learning models and 5G communication for faster and more precise object recognition, with a backup system to ensure timely and accurate decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the self-moving device uses on-device recognition technology, then the response speed is faster, but the recognition accuracy is insufficient in complex environments
Solution Approach 1:
The patent introduces a server as an intermediary between the self-moving device and the recognition task. The device captures images and transmits them to the server, which performs the recognition and returns results. This mediator approach allows the device to maintain fast local response while leveraging the server's superior recognition accuracy for complex environments.
Solution Approach 2:
The patent shifts the recognition task from the spatial dimension (on-device processing) to the network dimension (cloud-based processing). By utilizing the 5G network connection, the system accesses additional computational resources and recognition algorithms on the server, effectively adding a new dimension to the recognition capability.
2Measurement precision
If the self-moving device transmits images to a server for recognition, then the recognition accuracy improves, but the response time increases due to network communication
Solution Approach 1:
The patent implements preliminary actions by pre-establishing 5G network connections and pre-configuring the server recognition system. The fast 5G connection is prepared in advance to minimize transmission delays, and the server is pre-configured with recognition algorithms ready for immediate execution when images are received.
Solution Approach 2:
The patent changes the network communication parameter from traditional 4G or Wi-Fi to 5G technology. This parameter change provides significantly faster data transmission speeds and lower latency, reducing the time penalty associated with cloud-based recognition while maintaining high accuracy.
3Device complexity
If the self-moving device relies solely on its own recognition capability, then the system complexity is lower, but the reliability of operation in complex environments deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the server's recognition results are transmitted back to the self-moving device and used to adjust its actions. The device can compare its own recognition with the server's recognition and use the more reliable result, creating a feedback loop that continuously improves operational reliability without significantly increasing device complexity.
Solution Approach 2:
The patent provides beforehand cushioning by having the server recognition system ready as a backup support. When the device's own recognition is uncertain or the environment is complex, the pre-configured server system provides a safety cushion that prevents erroneous actions, thereby improving reliability without requiring the device to handle all recognition complexity itself.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The embodiments relate to a self-moving device, moving and working in a working area, including: an image detection module, detecting an environment around the self-moving device to generate an environmental image; a first recognition module, recognizing a specific object in the image based on the environmental image to generate a first recognition signal; a first communication module, selectively sending the environmental image and/or the first recognition signal to a server and receiving a second recognition signal corresponding to the environmental image; and a control module, controlling an action of the self-moving device according to the first recognition signal and/or the second recognition signal. Beneficial effects of embodiments are as follows: It is ensured that the self-moving device can obtain an accurate recognition result in time and performs an action accordingly.