包含版本:Hierarchical Task Network Planning AI 5.3 分层任务网络计划人工智能

使用这种灵活、全功能的行为树替代方案,创建可以提前计划的人工智能

HTN计划插件让你创建一个人工智能,它可以通过预测行动的后果来提前计划多个步骤。

就像行为树一样,您可以从C++或Blueprints轻松创建任务、装饰器和服务,并在可视化图形编辑器中排列它们。HTN规划器使用黑板数据来存储关于可能的未来世界状态的知识。节点在规划期间检查和修改worldstate中的值,这使得基于可能的未来状态做出决策成为可能。计划者有效地找到成本最低的计划,或优先级最高的计划。

与其他规划技术相比,如面向目标的行动规划,HTN规划更有效,给设计师更多的控制人工智能。它可以像行为树一样僵硬,也可以像GOAP一样灵活。你可以根据自己的需要创造出自主和灵活的人工智能:在预定义的任务序列中进行选择的人工智能,或者自由地以任何顺序安排任务以实现目标的人工智能,或者介于两者之间的任何人工智能。


Features:

Node-based HTN graph editor
Seamlessly use Blackboard data as worldstate
Make custom Tasks, Decorators, and Services in both C++ and Blueprints
Create composable behaviors using subnetworks
Make subplans within plans to freely mix planning and on-the-fly decision-making
Cost-based or priority-based planning
Parallel planning
Any-order planning
Integration with the Visual Logger, including visualizing the current plan
Integration with the Environment Query System for complex movement planning and decision-making
Realtime debugging features
Extend the HTN Component with HTN Extensions
Full source code access

For more info, check out the documentation website, the tutorials, and the official Discord community.

技术细节
Code Modules:

HTN [Runtime]
HTNEditor [Editor]

Number of Blueprints: 0

Number of C++ Classes: 70

Network Replicated: No (not needed for AI)

Supported Development Platforms: Windows, macOS, Linux

Supported Target Build Platforms: Windows 64-bit, macOS, Linux, Android, iOS

Documentation: HTN Documentation

Example Project: HTN Example Project

标签
TOOLKITEDITORTOOLSAIGRAPH EDITORTACTICSEDITOR TOOLHTNNODE EDITORPLANNINGCODE PLUGINGOAP

发表回复

后才能评论