AI Action Path Generation for Automated Avatar Traversal Testing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video game development processes require significant resource allocation for iterative testing and adjustment of levels due to the guesswork involved in ensuring that player avatars can traverse levels as intended, especially with procedural generation, leading to potential issues in quality assurance.
Innovation Solution
A system and method for generating and testing action paths for avatar traversal using map and object data, incorporating machine learning to evaluate feasibility and constraints, reducing the need for manual testing and optimizing level design.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual testing by human QA play-testers is used, then quality assurance can be performed, but resource consumption and time required increase significantly
Solution Approach 1:
The system enables self-service quality assurance by automatically generating action paths and evaluating feasibility using AI/ML models. The level design system performs its own testing without requiring human QA play-testers, thereby maintaining quality assurance while significantly reducing resource consumption and time requirements.
Solution Approach 2:
The patent replaces the mechanical process of manual human testing with an automated computational system. AI/ML models generate action paths and evaluate feasibility algorithmically, substituting the mechanical effort of human play-testers with automated processing that achieves the same quality assurance objectives more efficiently.
2Reliability
If iterative testing is performed manually, then level traversal can be validated, but development time increases
Solution Approach 1:
The system implements continuous automated validation through iterative generation and evaluation of action paths. The AI/ML models continuously generate new action paths and assess feasibility without interruption, providing ongoing validation of level traversal while eliminating the time-consuming manual iteration process.
Solution Approach 2:
The system performs preliminary automated testing during the development process itself, before final release. By generating and evaluating action paths in advance using AI/ML models, the system validates level traversal early in the development cycle, eliminating the need for time-consuming manual testing iterations later.
3Productivity
If procedural generation is used for level design, then level creation efficiency improves, but guesswork about avatar traversal increases
Solution Approach 1:
The system incorporates feedback mechanisms where AI/ML models continuously evaluate generated action paths against the level design and avatar moveset. This feedback loop identifies feasibility issues with avatar traversal and allows for automated adjustments, maintaining the efficiency benefits of procedural generation while ensuring traversal feasibility through iterative evaluation and refinement.
Data Source
AI summary
A system uses map data of a virtual environment and object data of an avatar object including a moveset to generate an action path for traversal of the virtual environment by the avatar object. The system applies machine learning model(s) to generate one or more pathways through the virtual environment, and decompose the one or more pathways into one or more pathway segments that can be evaluated for feasibility and other factors. The system can iteratively generate and evaluate a move sequence of the action path having one or more parameters for execution by the avatar object. The system can construct the action path by combination of a plurality of pathway segments to satisfy one or more constraints associated with traversal by the avatar object from a start location to a destination location within the virtual environment.