Mobile Telerobot RSS Prediction via Virtual Source Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional RSS prediction systems for mobile telerobots are inefficient for real-time telepresence applications due to high computational complexity, dependency on prior knowledge of radio source locations, and inability to handle dynamic environments, leading to potential loss of connectivity and increased navigation time.
Innovation Solution
A radio-source agnostic RSS prediction algorithm using a 'virtual radio source' concept, which performs zero-knowledge prediction of future connectivity without requiring training phases, utilizing a novel approach of virtual AP localization through 360-degree rotation and Trilateration-based localization techniques to minimize prediction error.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional offline RSS prediction systems are used, then prediction accuracy is improved, but real-time efficiency and computational speed deteriorate
Solution Approach 1:
The system dynamically adapts the prediction model by switching between different computational approaches based on current operational context. The online prediction system updates parameters in real-time as the telerobot moves, allowing accurate RSS predictions without requiring complete offline pre-computation for all possible scenarios.
Solution Approach 2:
The invention changes the fundamental parameters of the prediction system by moving from static offline models to dynamic online models. Key parameters such as prediction horizon, update frequency, and computational complexity are adjusted based on real-time requirements, enabling both accuracy and efficiency.
2Measurement precision
If Gaussian Processes or linear regression models are used for online RSS prediction, then prediction accuracy is improved, but device complexity and computational requirements increase
Solution Approach 1:
The system extracts only the essential computational elements needed for accurate RSS prediction, removing unnecessary complexity from full Gaussian Processes models. By focusing on key predictive features and using simplified models where appropriate, the system achieves good accuracy with reduced computational burden suitable for embedded devices.
Solution Approach 2:
The prediction system is segmented into multiple components with different computational complexities. Simple linear models are used for immediate predictions, while more complex models are applied only when needed for validation or in specific scenarios, dividing the computational task into manageable segments.
3Measurement precision
If prior knowledge of radio source location is required for RSS prediction, then prediction accuracy is improved, but adaptability to unknown environments deteriorates
Solution Approach 1:
The system performs preliminary actions by collecting RSS measurements and estimating radio source locations during the initial phase of operation. This preliminary data collection enables the system to build environment-specific models that improve prediction accuracy while maintaining adaptability to new environments through automated learning.
Solution Approach 2:
The prediction system serves itself by automatically adapting to new environments without requiring manual configuration of radio source locations. The system uses its own measurements to learn environment characteristics and adjust prediction parameters, enabling both accuracy and adaptability.
4Area of stationary object
If telerobot navigates through dynamic environment with obstacles, then coverage area is improved, but connectivity stability deteriorates due to signal variations
Solution Approach 1:
The system performs preliminary RSS predictions for future positions along the navigation path before the telerobot actually reaches those positions. This allows the remote operator to anticipate connectivity issues and plan alternative routes in advance, maintaining both coverage area and connectivity stability.
Solution Approach 2:
The system continuously monitors actual RSS measurements and compares them with predictions, using this feedback to refine future predictions and alert the operator to potential connectivity problems. This feedback loop maintains connectivity stability while allowing extensive navigation coverage.
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
This disclosure relates generally to a method and system for sensing best-connected future path for a mobile telerobot based on radio signal strength (RSS) prediction algorithm through in-situ radio-sensing. State-of-the-art methods predict the future path from the plurality of possible paths based on a radio-source in the environment. However, prediction of the suitable future path in the absence of the radio-source or in no signal zone is not yet achieved. The proposed in-situ algorithm is based on Log-Normal Shadowing Model (LNSM) and found efficient for prediction error minimization. The method enables the mobile telerobot to predict the future path on a trajectory of the telerobot even without prior knowledge of a radio-source location. The mobile telerobot can predict the most suitable path from a plurality of possible paths for a move based on virtual location estimation.