Autonomous Action Switching Under Environmental Uncertainty
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous systems struggle to act appropriately in environments with uncertainty, as they require complete resolution of environmental uncertainty before taking action.
Innovation Solution
A control system that includes a reception module, self-recognition module, target action prediction module, and switching module to generate actions considering uncertainty by using self-recognition blocks and target action prediction models, allowing for actions to be generated based on self-recognition or target action selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous system waits for complete resolution of environmental uncertainty before acting, then the reliability of actions is improved, but the productivity and responsiveness of the system deteriorates
Solution Approach 1:
The system dynamically adjusts its decision-making approach based on the level of environmental uncertainty. When uncertainty is high, it uses self-recognition blocks to maintain reliable actions within known boundaries. When uncertainty is resolved, it transitions to target action prediction for more productive and responsive behavior, creating a dynamic balance between reliability and productivity
Solution Approach 2:
The system changes the parameter of uncertainty resolution completeness based on operational needs. Instead of always requiring complete uncertainty resolution, it adjusts the threshold for action based on whether self-recognition or target-action prediction is being used, allowing actions to proceed at appropriate levels of certainty
2Productivity
If the autonomous system uses target action prediction to act in uncertain environments, then the productivity is improved, but the reliability of actions deteriorates
Solution Approach 1:
Self-recognition blocks serve as an intermediary between the environment and target action prediction. They define boundaries of predictability and controllability that constrain target action prediction, ensuring it only operates within reliable zones while still enabling productive action in uncertain environments
3Reliability
If the system defines a self-recognition block based on predictability and controllability ranges, then the reliability of actions in uncertain environments is improved, but the device complexity increases
Solution Approach 1:
The system segments the operational space into self-recognition blocks based on predictability and controllability ranges. Each block represents a discrete region where specific actions are reliable, dividing the complex uncertain environment into manageable segments that can be handled with simpler control logic
Data Source
AI summary
To act appropriately in consideration of uncertainty of a surrounding environment, it is provided a control system for generating an action for controlling a controlled device, comprising: a reception module configured to receive sensor data acquired by observing a state of a surrounding environment of the controlled device; a self-recognition module configured to derive, through use of a self-recognition prediction model that predicts a self-range being a range having a predictability and a controllability relating to the controlled device, a self-recognition block that defines the self-range from the sensor data; a target action prediction module configured to derive, through use of a target action prediction model that predicts a target action of the controlled device, the target action from the sensor data; and a switching module configured to select one of the self-recognition block or the target action in order to generate an action of the controlled device.