Tele-Presence Robot Knowledge Partitioning Under Bandwidth Limits

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conversational tele-presence robots in geographically separated environments face limitations in information storage, processing speed, and network bandwidth, which hinder efficient task execution and decision-making, particularly in handling layered knowledge during task execution.

Innovation Solution

A processor-implemented method for knowledge partitioning that involves obtaining control commands, dynamically querying multiple storage devices (on-board memory, edge, cloud, and web interface) based on task type, generating execution plans, executing sub-tasks, and validating tasks while partitioning and storing knowledge across these devices for seamless subsequent task execution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If tele-presence robot stores more information locally to improve task execution autonomy, then information retrieval speed improves, but device complexity and storage requirements increase

Engineering Contradiction:
Improveinformation retrieval speedVSAvoidstorage capability
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent segments information storage across multiple hierarchical levels: local on-board storage for critical task execution data, edge storage for intermediate processing, and cloud storage for comprehensive knowledge bases. This segmentation allows the robot to retrieve information at appropriate speeds from each level without requiring all information to be stored locally, thus improving retrieval speed while managing device complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a spatial dimension to information storage by distributing data across multiple geographic locations (local device, edge server, cloud infrastructure). This multi-dimensional storage architecture enables the system to access information from the nearest available location, improving retrieval speed without proportionally increasing local storage requirements.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If tele-presence robot processes more information locally to improve decision-making accuracy, then task execution accuracy improves, but processing speed decreases due to bandwidth limitations

Engineering Contradiction:
Improvedecision-making accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The patent segments processing tasks across multiple levels: critical time-sensitive processing occurs locally on the robot, intermediate processing occurs at edge servers, and comprehensive analysis occurs in the cloud. This segmentation allows accurate processing of complex information while maintaining overall processing speed by handling different task types at appropriate locations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements preliminary processing of information at edge and cloud levels before transmission to the robot. By pre-processing and filtering information remotely, the system reduces the amount of data that needs to be transmitted and processed locally, thereby improving both processing speed and decision-making accuracy.

Inventive Principle:
Principle #10Preliminary action

3Quantity of substance

If tele-presence robot uses high bandwidth network for information transfer, then information availability improves, but network congestion occurs affecting manual control and other functionalities

Engineering Contradiction:
Improveinformation availabilityVSAvoidmanual control reliability
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent segments information transfer into different priority levels and channels: critical control commands use dedicated low-latency channels, while bulk information transfer uses available bandwidth. This segmentation ensures that information availability is maintained while preventing network congestion from degrading manual control reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary filtering and prioritization of information before transmission. By pre-processing information to identify what is truly necessary for transmission versus what can be accessed locally or processed asynchronously, the system improves information availability while reducing network load and maintaining control reliability.

Inventive Principle:
Principle #10Preliminary action

4Loss of information

If tele-presence robot queries multiple storage devices dynamically to improve information completeness, then task execution completeness improves, but time consumption increases

Engineering Contradiction:
Improveinformation completenessVSAvoidtime consumption
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent segments the information retrieval process into hierarchical queries: first checking local on-board storage for immediate needs, then edge storage for intermediate information, and finally cloud storage for comprehensive data. This segmented approach ensures information completeness while minimizing time consumption by accessing the nearest available information sources first.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements preliminary assessment of information availability at each storage level before initiating queries. By pre-evaluating what information is locally available versus what requires remote queries, the system reduces unnecessary query operations and minimizes time consumption while maintaining information completeness.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3881988A1Knowledge partitioning for task execution by conversational TELE-presence robots in a geographically separated environment
Publication Date: 2021.09.22 TATA CONSULTANCY SERVICES LTD
  • EP3881988A1 patent drawingFigure 1
  • EP3881988A1 patent drawingFigure 2
  • EP3881988A1 patent drawingFigure 3

AI summary

Conventional tele-presence robots have their own limitations with respect to task execution, information processing and management. Embodiments of the present disclosure provide a tele-presence robot (TPR) that communicates with a master device associated with a user via an edge device for task execution wherein control command from the master device is parsed for determining instructions set and task type for execution. Based on this determination, the TPR queries for information across storage devices until a response is obtained enough to execute task. The task upon execution is validated with the master device and user. Knowledge acquired, during querying, task execution and validation of the executed task, is dynamically partitioned by the TPR across storage devices namely, on-board memory of the tele-present robot, an edge device, a cloud and a web interface respectively depending upon the task type, operating environment of the tele-presence robot, and other performance affecting parameters.