Autonomous System Knowledge-Based Reasoning for Abnormal Event Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous systems face challenges in adaptability, behavior appropriateness to their environment, and objective generation, particularly in identifying abnormal events and generating effective responses.

Innovation Solution

A knowledge-based reasoning method that utilizes multiple databases to assess and generate active objectives by comparing dynamic environment properties with static and common-sense rules, allowing autonomous systems to detect incoherent events and generate corrective actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If autonomous systems use predefined rules for detecting abnormal events, then the system structure is simple, but the adaptability to different environments is poor

Engineering Contradiction:
ImproveadaptabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system dynamically adapts its behavior by adjusting the weight coefficients of different rules based on environmental context. Instead of using fixed predefined rules, the system continuously updates rule weights to match current environmental conditions, enabling adaptability without requiring complete reconfiguration of the system structure.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes parameters (rule weights) rather than changing the fundamental rule structure. By modifying the importance weights of existing rules based on environmental context, the system achieves adaptability while maintaining a relatively simple underlying rule framework, thus resolving the contradiction between adaptability and complexity.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If autonomous systems perform comprehensive coherence checking, then the accuracy of abnormal event detection is improved, but the computational time increases

Engineering Contradiction:
Improvedetection accuracyVSAvoidcomputational time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs partial coherence checking by selectively applying coherence checks only to rules with higher weights or those most relevant to the current situation. Instead of checking all rules comprehensively, the system focuses computational resources on the most critical checks, maintaining detection accuracy while reducing overall computational time.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system skips coherence checks for rules with very low weights or those deemed irrelevant based on environmental context. By rushing through or skipping unnecessary checks, the system reduces computational overhead while still maintaining adequate detection accuracy for the most important events.

Inventive Principle:
Principle #21Skipping (Rushing through)

3Adaptability or versatility

If autonomous systems generate multiple candidate objectives, then the suitability of objective generation is improved, but the complexity of objective selection increases

Engineering Contradiction:
Improveobjective generation suitabilityVSAvoidobjective selection complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system uses feedback from environmental monitoring and coherence checking results to dynamically adjust the generation and selection of candidate objectives. By incorporating feedback loops that evaluate the effectiveness of generated objectives, the system can refine its objective selection process, improving suitability while managing complexity through iterative learning rather than complex upfront decision-making.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4113395A1System and method for knowledge-based reasoning of an autonomous system
Publication Date: 2023.01.04 ECOLE NAT SUPERIEURE DINGS DE CAEN
  • EP4113395A1 patent drawingFigure 1
  • EP4113395A1 patent drawingFigure 2
  • EP4113395A1 patent drawingFigure 3

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.