Behavior Tree(行为树)研究综述
Behavior Tree 行为树 - Here, we show that genetic programming can be effectively used to learn the structure of a behavior tree (BT) to solve a robotic task in an unpredictable environment. [1] There is a growing interest in Behavior Trees (BTs) as a tool to describe and implement robot behaviors. [2] In this work, we develop a set of behavioral and conditional modules for the use with behavior trees. [3] In this letter, we provide a formal framework for comparing the expressive power of Behavior Trees (BTs) to other action selection architectures. [4] In the present article, we fill the gap by (a) establishing the specifications of skills that can be sequenced with partial executions, (b) proposing an implementation based on the combination of finite-state machines and behavior trees, and (c) demonstrating the benefits of such skills through extensive trials in the environment of ARIAC (Agile Robotics for Industrial Automation Competition). [5] A Behavior Tree is then used to extend this framework to include additional behaviors which improve the system's robustness and enable the operator to override if requested. [6] On the other hand, Behavior Trees provide a mathematical model for specifying plan execution in an intrinsically composable, reactive, and robust way. [7] This paper proposes a novel dynamic method based on Behavior Trees (BTs) that integrates planning and allocation of tasks in mixed human robot teams, suitable for manufacturing environments. [8] Behavior Trees (BTs) have become a valuable tool for the development of the decision-making aspect for automated agents, such as the Non-Player Characters (NPCs) in computer games, and more recently, the agents of the highly automated robotic applications. [9] We introduce a dynamically reconfigurable planning methodology with behavior tree-based control strategies toward reactive TAMP, which takes the advantage of previous plans and incremental graph search during temporal logic-based reactive synthesis. [10] It combines different well-known approaches and is inspired by behavior trees as well as hierarchical state machines. [11] The architecture has been built around explainable, modular representations (relational graphs and behavior trees) to ease the upgradability of the system and AI modules to adapt to realistic and complex settings. [12] Further, we present a behavior tree based control architecture to efficiently integrate these different modalities. [13] Several technical modules, including object detection, object tracking, georeferencing, and behavior tree, are integrated as a mobile robot system and implemented on a commercial micro UAV. [14] To generate explanations for robot behavior, we propose using Behavior Trees (BTs), which are a powerful and rich tool for robot task specification and execution. [15] Behavior Trees (BTs) are becoming a popular tool to model the behaviors of autonomous agents in the computer game and the robotics industry. [16] We present our computational model based on behavior trees uniformly for scripting agent interaction, user interaction, and narrative events; our stand-alone authoring tool, which provides an integrated development and testing environment for authoring with this model; and our JavaScript API for web-based development, demonstrating the expressiveness and simplicity of our approach through two case studies. [17] By making the evolved controllers human‐understandable using behavior trees, the controllers can be queried, explained, and even improved by a human user. [18] The proposed system relies on a Behavior Tree (BT) framework that combines the knowledge of EMS protocol guidelines with speech recognition, natural language processing, and machine learning methods to (i) extract critical information from responders’ conversations and verbalized observations, (ii) infer the incident context, and (iii) decide on safe and effective response interventions to perform. [19] In order to enhance scalability and modularity, the modeling of both the autonomous and remote-controlled robot behaviors are performed using a Behavior Tree (BT) approach. [20] Frameworks such as Behavior Trees are flexible but difficult to characterize, especially when designing reactions and recovery behaviors to consistently converge to a desired goal condition. [21] This paper firstly fused the NPC features of the game with the DTS system and established NPC model and behavior tree in DTS. [22] By analyzing the characteristics of MOBA games and the advantages of implementing hierarchical logic through behavior tree, this paper studies the role of behavior tree in the decision-making system of MOBA game AI design, so as to help game developers design games that meet the needs of players. [23] Behavior Trees (BTs) are gaining acceptance in robotics to specify action policies at the deliberative level. [24] Unlike the traditional logical operator based reasoning rules, rules with the aid of ontology and behavior tree are constructed, which have formulated the complex reasoning of the target tracking. [25] In this paper, we will introduce standard behavior algorithms in videogames, such as Finite-State Machines and Behavior Trees, as well as more recent developments, such as Monte-Carlo Tree Search. [26] As a result of this approach, the behavior tree is presented, a schematic diagram for the purpose of planning behavioral interventions. [27] Behavior tree will be a good medium for the application of artificial intelligence in the military field. [28] In the next couple of sections, we’ll give a brief overview of two of these techniques: behavior trees and planners. [29] In this paper, we show how a planning algorithm can be used to automatically create and update a Behavior Tree (BT), controlling a robot in a dynamic environment. [30] To verify the feasibility and real-time performance of a network trip strategy based on multi protection IEDs, a modeling and real time analysis method of the protection system based on behavior trees is proposed. [31] Behavior trees are proposed as an alternative representation of high level task. [32] In this paper, we formalize the problem of multi-robots fulfilling dynamic tasks using state transitions represented through a Behavior Tree. [33] While there are many different architectures for an AI programmer to pick from, behavior trees are one of the most popular algorithms for implementing NPC action selection in games due to their simplicity to code and use. [34] This paper proposed an autonomous task algorithm based on Behavior Trees (BTs) for robot, which enabled robot to complete tasks autonomously in dynamic environment with understanding user's intention. [35] This paper introduces an algorithm that evolves problem-specific swarm behaviors by combining multi-agent grammatical evolution and Behavior Trees (BTs). [36] We developed IKBT, a knowledge-based intelligent system that can mimic human experts’ behaviors in solving closed-from inverse kinematics using Behavior Tree. [37]在这里，我们展示了遗传编程可以有效地用于学习行为树 (BT) 的结构，以解决不可预测环境中的机器人任务。 [1] 人们对行为树 (BT) 作为描述和实现机器人行为的工具越来越感兴趣。 [2] 在这项工作中，我们开发了一组用于行为树的行为和条件模块。 [3] 在这封信中，我们提供了一个正式的框架，用于将行为树 (BT) 的表达能力与其他动作选择架构进行比较。 [4] 在本文中，我们通过 (a) 建立可以通过部分执行排序的技能规范来填补这一空白，(b) 提出基于有限状态机和行为树组合的实现，以及 (c) 演示通过在 ARIAC（工业自动化竞赛敏捷机器人）环境中的广泛试验，这些技能的好处。 [5] 然后使用行为树来扩展此框架以包含其他行为，这些行为可提高系统的稳健性并使操作员能够在请求时覆盖。 [6] 另一方面，行为树提供了一个数学模型，用于以本质上可组合、反应性和稳健的方式指定计划执行。 [7] 本文提出了一种基于行为树 (BT) 的新型动态方法，该方法集成了混合人类机器人团队中任务的规划和分配，适用于制造环境。 [8] 行为树 (BT) 已成为开发自动化代理决策方面的宝贵工具，例如计算机游戏中的非玩家角色 (NPC)，以及最近高度自动化机器人应用程序的代理。 [9] 我们引入了一种动态可重构的规划方法，该方法具有基于行为树的控制策略，用于响应式 TAMP，它利用了以前的计划和基于时间逻辑的响应式合成期间的增量图搜索。 [10] 它结合了不同的知名方法，并受到行为树和分层状态机的启发。 [11] 该架构围绕可解释的模块化表示（关系图和行为树）构建，以简化系统和 AI 模块的可升级性，以适应现实和复杂的设置。 [12] 此外，我们提出了一种基于行为树的控制架构，以有效地整合这些不同的模式。 [13] 几个技术模块，包括对象检测、对象跟踪、地理参考和行为树，被集成为一个移动机器人系统，并在商用微型无人机上实现。 [14] 为了生成机器人行为的解释，我们建议使用行为树 (BT)，它是用于机器人任务规范和执行的强大而丰富的工具。 [15] 行为树 (BT) 正在成为一种流行的工具，用于模拟计算机游戏和机器人行业中自主代理的行为。 [16] 我们基于行为树统一呈现我们的计算模型，用于脚本代理交互、用户交互和叙述事件；我们的独立创作工具，它为使用此模型进行创作提供了一个集成的开发和测试环境；以及我们用于基于 Web 的开发的 JavaScript API，通过两个案例研究展示了我们方法的表现力和简单性。 [17] 通过使用行为树使进化的控制器易于理解，人类用户可以查询、解释甚至改进控制器。 [18] 所提出的系统依赖于行为树 (BT) 框架，该框架将 EMS 协议指南的知识与语音识别、自然语言处理和机器学习方法相结合，以 (i) 从响应者的对话和口头观察中提取关键信息，(ii)推断事件背景，以及 (iii) 决定要执行的安全有效的响应干预措施。 [19] 为了增强可扩展性和模块化，自主和遥控机器人行为的建模使用行为树 (BT) 方法进行。 [20] 诸如行为树之类的框架很灵活，但难以表征，尤其是在设计反应和恢复行为以始终收敛到所需的目标条件时。 [21] 本文首先将游戏的NPC特征与DTS系统融合，在DTS中建立了NPC模型和行为树。 [22] 通过分析MOBA游戏的特点以及通过行为树实现层次逻辑的优势，研究行为树在MOBA游戏AI设计决策系统中的作用，以帮助游戏开发者设计出符合需求的游戏。的玩家。 [23] 行为树 (BT) 正在机器人技术中获得认可，以在审议级别指定行动策略。 [24] 不同于传统的基于逻辑算子的推理规则，借助本体和行为树构建规则，形成了目标跟踪的复杂推理。 [25] 在本文中，我们将介绍视频游戏中的标准行为算法，例如有限状态机和行为树，以及最近的发展，例如蒙特卡洛树搜索。 [26] 作为这种方法的结果，呈现了行为树，这是一个用于规划行为干预的示意图。 [27] 行为树将是人工智能在军事领域应用的良好媒介。 [28] 在接下来的几节中，我们将简要概述其中两种技术：行为树和规划器。 [29] 在本文中，我们展示了如何使用规划算法自动创建和更新行为树 (BT)，从而在动态环境中控制机器人。 [30] 为了验证基于多保护IED的网络跳闸策略的可行性和实时性，提出了一种基于行为树的保护系统建模和实时分析方法。 [31] 行为树被提议作为高级任务的替代表示。 [32] 在本文中，我们使用通过行为树表示的状态转换来形式化多机器人完成动态任务的问题。 [33] 虽然 AI 程序员有许多不同的架构可供选择，但由于其代码和使用简单，行为树是在游戏中实现 NPC 动作选择的最流行的算法之一。 [34] 本文提出了一种基于行为树（BTs）的机器人自主任务算法，使机器人能够在了解用户意图的动态环境中自主完成任务。 [35] 本文介绍了一种算法，该算法通过结合多智能体语法进化和行为树（BTs）来进化特定问题的群体行为。 [36] 我们开发了 IKBT，这是一个基于知识的智能系统，它可以模仿人类专家在使用行为树解决封闭逆运动学时的行为。 [37]
Use Behavior Tree
The proposed framework uses behavior trees to design behaviors that have safety properties and uses vehicle states to determine best risk control response. [1] Moreover, special attention is given to the interaction between the task and motion levels, where we use behavior tree as an intermediate interface to execute the plan, feedback the execution outcome and facilitate the high-level task re-planning process. [2]提议的框架使用行为树来设计具有安全属性的行为，并使用车辆状态来确定最佳风险控制响应。 [1] 此外，我们特别关注任务和运动级别之间的交互，我们使用行为树作为中间接口来执行计划，反馈执行结果并促进高层任务重新计划过程。 [2]
behavior tree framework 行为树框架
Based on the Behavior Tree framework, we create a modular and easily extendable action sequence with the goal of finding a person to assist the robot. [1] We present a behavior tree framework that can intelligently pick the best available global localisation method from amongst visual features, lidar landmarks and GPS. [2]基于行为树框架，我们创建了一个模块化且易于扩展的动作序列，目标是找到一个人来协助机器人。 [1] 我们提出了一个行为树框架，可以从视觉特征、激光雷达地标和 GPS 中智能地选择最佳可用的全球定位方法。 [2]