Robotic Sensing Validation Using Real-Time Human Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robotic sensing systems often fail to accurately detect and classify objects in real-life scenarios due to challenges like lighting, occlusion, and view angle, and consumers lack the ability to evaluate their accuracy and confidence, which is critical for safe operation.

Innovation Solution

A real-time interface that allows robots to interact with nearby humans or devices for improving object detection and classification by providing audio and text-based communication, enabling verification, adaptation, and updating of sensing models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If robotic sensing systems operate autonomously without human intervention, then productivity and speed are improved, but measurement precision and reliability deteriorate due to inability to accurately detect and classify objects in real-life scenarios

Engineering Contradiction:
Improveoperational speedVSAvoidobject detection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system implements a feedback mechanism where detection results are communicated to nearby humans or devices, and their responses are used to verify and improve the accuracy of object detection and classification. This closed-loop feedback allows the robot to learn from human corrections while maintaining autonomous operation.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary communication interface that connects the robotic sensing system with nearby humans or devices. This intermediary allows for real-time verification of detection results without requiring direct human control, bridging the gap between autonomous operation and human expertise.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If robotic sensing systems increase automation for autonomous operation, then ease of operation is improved, but reliability deteriorates due to lack of human evaluation capability

Engineering Contradiction:
Improveautonomous operation capabilityVSAvoiddetection reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs self-validation by automatically communicating detection results and requesting verification from nearby humans or devices. This self-service mechanism maintains autonomous operation while incorporating human evaluation to improve reliability, without requiring continuous human supervision.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If robotic sensing systems incorporate real-time human feedback for verification, then measurement precision and reliability are improved, but device complexity increases due to additional communication interfaces

Engineering Contradiction:
Improveobject classification accuracyVSAvoidcommunication interface complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The communication interface is designed to be universal and multi-functional, capable of interacting with various types of nearby devices and humans through standardized protocols. This universality reduces the need for multiple specialized interfaces, thereby limiting the increase in device complexity while still enabling real-time feedback for improved measurement precision.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250306596A1Real-time validation of robotic sensing systems
Publication Date: 2025.10.02 INTEL CORP
  • US20250306596A1 patent drawing
  • US20250306596A1 patent drawing
  • US20250306596A1 patent drawing

AI summary

Disclosed herein are systems, devices, and apparatuses for improved perception/sensing systems in robots or other vehicles. The system receives sensor data representative of a field of view of a robot and determines, based on the sensor data and an object detection model, an identification of an object within the field of view and an accuracy metric of the identification of the object, wherein the object detection model relates the sensor data to the identification. The system also requests, based on the accuracy metric, an informational feedback from the identification of the object and updates the object detection model to an updated object detection model based on the informational feedback.