Autonomous Knowledge Reasoning for Abnormal Event Objectives
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous systems face challenges in adaptability, behavior appropriateness to their environment, and unsuitability in identifying abnormal events and generating objectives to address them.
Innovation Solution
A computer-implemented method for knowledge-based reasoning that involves accessing static and dynamic environment properties, coherence checking, and generating active objectives using databases and common-sense rules to identify incoherent events and create corrective action strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If autonomous systems use predefined rules and algorithms for decision-making, then they can operate autonomously, but they lack adaptability to abnormal events and environmental changes
Solution Approach 1:
The patent introduces a knowledge base as an intermediary component between the autonomous system and the environment. This knowledge base stores static environment properties, dynamic environment properties, and coherence rules that mediate the system's decision-making process. When an abnormal event occurs, the system queries the knowledge base to determine coherence and generate appropriate objectives, enabling adaptability without requiring complete reprogramming of the autonomous system.
Solution Approach 2:
The patent implements dynamic environment properties that can be updated based on observed events, allowing the system to adapt its behavior. The coherence checking mechanism dynamically evaluates whether new events are consistent with the knowledge base, and the objective generation process dynamically creates new tasks based on incoherent events. This dynamic adaptation enables the system to respond to abnormal events while maintaining a structured approach.
2Adaptability or versatility
If autonomous systems operate with fixed behavior patterns, then system operation is simple, but the behavior is inappropriate for the given environment
Solution Approach 1:
The patent pre-populates the knowledge base with static environment properties, common-sense rules, and candidate objectives before the autonomous system operates. This preliminary preparation allows the system to quickly adapt to environmental changes during operation without complex real-time processing. The coherence rules are pre-defined to guide the system's environmental adaptation, reducing the operational complexity while maintaining adaptability.
Solution Approach 2:
The patent implements a feedback mechanism where the autonomous system observes events, checks their coherence against the knowledge base, and generates new objectives based on incoherent events. This closed-loop feedback process enables the system to continuously adapt its behavior to the environment. The system monitors environmental changes, evaluates coherence, and adjusts its objectives accordingly, achieving environmental adaptability through systematic feedback rather than complex operation.
3Reliability
If autonomous systems use complex reasoning to identify abnormal events and generate objectives, then they can respond appropriately, but the processing time increases
Solution Approach 1:
The patent segments the reasoning process into distinct modules: event observation, coherence checking against static and dynamic properties, abnormal event identification, and objective generation from candidate objectives. This segmentation allows each module to focus on a specific task, improving processing efficiency. The knowledge base is also segmented into static properties, dynamic properties, and coherence rules, enabling targeted queries rather than comprehensive analysis, thus reducing processing time while maintaining detection accuracy.
Solution Approach 2:
The patent applies partial coherence checking by focusing on specific aspects of events relevant to the current context rather than analyzing all possible properties. The system generates objectives from a pre-defined set of candidate objectives rather than creating objectives from scratch, which reduces processing time. This partial action approach maintains reliable abnormal event detection by focusing on critical coherence aspects while avoiding unnecessary processing of irrelevant details.
4Loss of information
If autonomous systems maintain comprehensive knowledge bases, then they can make informed decisions, but the storage requirements and computational overhead increase
Solution Approach 1:
The patent extracts only the essential environmental properties and coherence rules needed for autonomous operation into the knowledge base, rather than storing complete environmental models. The static environment properties contain fundamental characteristics, while dynamic properties store only relevant changes. This extraction reduces knowledge base complexity while maintaining sufficient information for informed decision-making about abnormal events and objective generation.
Solution Approach 2:
The knowledge base is designed with multi-functional components that serve multiple purposes. The static environment properties are used for both initial system configuration and ongoing coherence checking. The coherence rules serve both to detect abnormal events and to guide objective generation. This universality reduces the overall knowledge base complexity by eliminating redundant information while maintaining comprehensive environmental understanding for informed decisions.
Data Source
AI summary
Methods of and systems for knowledge-based reasoning to establish a list of active objectives by an autonomous system. The method comprises accessing a list of active objectives; accessing a first database populated with static environment properties, the static environment properties defining properties of entities, the entities defining an environment in which the autonomous system is configured to operate; accessing a second database populated with dynamic environment properties comprising third computer-readable instructions generated by the autonomous system based on events having been observed by the autonomous system. Upon observing a new event, a new dynamic environment property is generated based on the new event and coherence checking is executed to assess whether the new dynamic environment property conflicts with at least one of the static environment properties, and, if so, the new dynamic environment property being identified as incoherent.