Robot Safety Assessment Using Human-Aware Risk Scoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional robots in collaborative environments often have limited sensing, processing, and decision-making capabilities, leading to inefficient operations and potential safety hazards due to frequent stoppages when interacting with humans, as they may not be able to assess and react to complex interactions effectively.

Innovation Solution

A safety system that monitors the environment, determines human attributes and behaviors, and adapts the robot's actions to mitigate safety risks through real-time risk assessment, using sensors like depth sensors, cameras, and AI learning models to adjust motion and prevent collisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the robot uses simple stop-when-person-detected safety mechanism, then safety is ensured, but productivity decreases due to frequent stoppages

Engineering Contradiction:
ImprovesafetyVSAvoidoperational efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system changes the parameter of robot velocity dynamically based on detected human attributes. Instead of binary stop/go decisions, the robot adjusts its speed continuously according to risk assessments, allowing safe operation without unnecessary stoppages

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements continuous feedback loops where sensor data about human presence and attributes is constantly monitored, risk is reassessed, and robot velocity is adjusted in real-time. This allows the robot to maintain safe operation while minimizing interruptions to productivity

Inventive Principle:
Principle #23Feedback

2Device complexity

If the robot has limited sensing and processing capabilities, then device complexity is reduced, but the ability to assess and react to complex interactions deteriorates

Engineering Contradiction:
Improvesensing and processing capabilitiesVSAvoidability to assess complex interactions
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The system segments the complex safety assessment task into distinct modules: human detection, attribute classification (child, elderly, pregnant, etc.), risk calculation, and velocity adjustment. Each module handles a specific aspect, making the overall system manageable despite complex functionality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary risk assessment layer that translates raw sensor data about human attributes into actionable velocity adjustments. This intermediary processing layer enables complex decision-making without requiring the robot to have advanced native intelligence

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If the robot stops operations frequently when persons are nearby, then safety is maintained, but loss of time increases

Engineering Contradiction:
ImprovesafetyVSAvoidoperational downtime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

Instead of complete stoppage (excessive action), the system applies partial action by adjusting velocity to a reduced but non-zero level. This allows the robot to maintain some level of operation while still ensuring safety, thereby reducing time loss

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4197710A1Situation-aware safety assessment of robot-human activities
Publication Date: 2023.06.21 INTEL CORP
  • EP4197710A1 patent drawingFigure 1
  • EP4197710A1 patent drawingFigure 2~3
  • EP4197710A1 patent drawingFigure 4

AI summary

Disclosed herein are systems, devices, and methods of a safety system for analyzing and improving the safety of collaborative environments in which a robot may interact a human. The safety system may determine a monitored attribute of a person within an operating environment of a robot, where the monitored attribute may be based on received sensor information about the person in the operating environment. In addition, the safety system may determine a risk score for the person based on the monitored attribute. The risk score may be defined by (1) a collision probability that the person will cause an interference during a planned operation of the robot and (2) a severity level associated with the interference. The safety system may also generate a mitigating instruction for the robot if the risk score exceeds a threshold level.