Robotic Variable Autonomy for Unanticipated Task Scenarios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic systems face challenges in achieving full autonomy due to unanticipated operational scenarios, such as varying lighting conditions, sensor failures, and unrecognized objects, which can lead to task failures and require human intervention.
Innovation Solution
The use of a process knowledge database to enable on-the-fly variable autonomy for robotic systems, allowing them to operate autonomously or semi-autonomously by generating contextual and semantic labels, and enabling human-robot collaborative teams to balance operational efficiency with risk.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If robotic systems operate autonomously without human involvement, then productivity is improved, but reliability deteriorates due to unanticipated operational scenarios
Solution Approach 1:
The patent introduces a human-in-the-loop intermediary control mechanism that mediates between autonomous robotic operation and human control. The system dynamically adjusts the level of human involvement based on situation assessment, allowing autonomous operation for routine tasks while enabling human intervention for unanticipated scenarios, thus resolving the contradiction between productivity and reliability
2Reliability
If humans directly control robotic systems, then reliability is improved through human judgment, but productivity deteriorates due to human error and slower operation
Solution Approach 1:
The patent implements dynamic control adjustment where the system transitions between autonomous and human-controlled modes based on real-time situation assessment. For routine, predictable tasks, the system operates autonomously at high speed, while for unanticipated or complex scenarios, it dynamically shifts to human control, optimizing both productivity and reliability contextually
3Productivity
If robotic systems are pre-programmed with full autonomy, then productivity is improved, but device complexity increases due to extensive programming requirements
Solution Approach 1:
The patent implements partial autonomy where the robotic system is programmed to handle only routine, predictable tasks autonomously, while leaving complex, unanticipated scenarios to human judgment. This partial automation approach achieves meaningful productivity improvements without requiring comprehensive programming for all possible scenarios, thus reducing device complexity
4Productivity
If robotic systems operate in remote locations, then productivity is improved by reducing human presence, but device complexity increases due to bandwidth and latency constraints
Solution Approach 1:
The patent segments control authority between autonomous robotic systems operating remotely and human operators. The robotic system independently handles routine operations and local decision-making, while human operators provide high-level guidance and handle exceptional scenarios. This segmentation reduces the complexity of real-time remote control communication while maintaining productive remote operation capability
Data Source
AI summary
Based on data indicative of an area proximate to a robotic device, a scene is generated. Based on information from a knowledge database, a task associated with the scene is identified. A risk threshold is determined based on the scene, the task, and one or more trust thresholds. Based on the risk threshold, a ratio of sub-tasks of the task to be controlled by a user is determined. In accordance with the risk threshold, a user input is received for controlling one or more of the sub-tasks when the ratio dictates that at least one of the sub-tasks requires user intervention.