Hybrid Robot Autonomy Control for Human Assistance Handover

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robotic systems lack the ability to determine when to request human assistance and do not provide a methodology for training robotic devices to reduce cognitive load on human users, leading to inefficiencies and reduced productivity in production-worthy robotics-based manufacturing and maintenance work.

Innovation Solution

A robotic device configured with a hybrid control architecture that includes dynamically changeable levels of autonomy, allowing for full autonomy, teleoperation by a human user, and shared control between the computer system and human user, enabling the device to determine when to seek assistance and reduce cognitive load through collaboration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If robots operate with full autonomy, then productivity is improved, but reliability deteriorates when encountering unrecognized situations

Engineering Contradiction:
Improvetask completion rateVSAvoidoperational reliability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system dynamically adjusts the level of autonomy based on the situation. The robot operates autonomously for routine tasks to maximize productivity, but automatically transitions to teleoperation mode when encountering unrecognized or critical situations, thereby maintaining reliability without sacrificing overall productivity

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The autonomy level is changed as a parameter based on environmental feedback. The robot monitors its confidence level in task execution and adjusts the autonomy parameter accordingly - maintaining high autonomy for familiar tasks and reducing to teleoperation when confidence drops below thresholds, thus balancing productivity and reliability

Inventive Principle:
Principle #35Parameter changes

2Reliability

If robots operate with complete teleoperation, then reliability is improved, but productivity deteriorates due to constant human intervention

Engineering Contradiction:
Improveoperational reliabilityVSAvoidtask completion rate
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

Instead of requiring complete human control, the system applies partial teleoperation only when necessary. The robot handles routine tasks autonomously and selectively engages human operators only for critical or unrecognized situations, reducing unnecessary human intervention while maintaining reliability when needed

Inventive Principle:
Principle #16Partial or excessive action

3Object-affected harmful factors

If robots use fragile autonomy that cuts off at unrecognized situations, then safety is improved, but productivity deteriorates due to frequent human takeover

Engineering Contradiction:
ImprovesafetyVSAvoidoperational efficiency
Core Design Contradiction:
Object-affected harmful factorsVSProductivity

Solution Approach 1:

The system continuously monitors environmental feedback and task progression to determine when human intervention is truly necessary. By using feedback loops to assess situation recognition confidence and task criticality, the robot avoids unnecessary teleoperation takeovers while maintaining safety, thus improving productivity without compromising harm prevention

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP2928649B1Human augmentation of robotic work
Publication Date: 2024.10.09 INTERNATIONAL ELECTRONIC MACHINES CORP
  • EP2928649B1 patent drawingFigure 1
  • EP2928649B1 patent drawingFigure 2
  • EP2928649B1 patent drawingFigure 3

AI summary

A solution for performing a set of tasks using one or more robotic devices is provided. The robotic device can be configured to perform each task using one or more effector devices, one or more sensor devices, and a hybrid control architecture including a plurality of dynamically changeable levels of autonomy. The levels of autonomy can include: full autonomy of the robotic device, teleoperation of the robotic device by a human user, and at least one level of shared control between the computer system and the human user.