A principled analysis of Behavior Trees and their generalisations

• URL: http://arxiv.org/abs/2008.11906v2
• Date: Tue, 25 May 2021 05:42:14 GMT
• Title: A principled analysis of Behavior Trees and their generalisations
• Authors: Oliver Biggar (1), Mohammad Zamani (1), Iman Shames (2) ((1) Defence Science and Technology Group, Australia, (2) The Australian National University, Australia)
• Abstract summary: We analyse the principles behind Behavior Trees (BTs), an increasingly popular tree-structured control architecture. We show that reasoning via these principles leads to compatible solutions. We introduce a new class of control architectures we call generalised BTs or $k$-BTs.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As complex autonomous robotic systems become more widespread, the need for transparent and reusable Artificial Intelligence (AI) designs becomes more apparent. In this paper we analyse how the principles behind Behavior Trees (BTs), an increasingly popular tree-structured control architecture, are applicable to these goals. Using structured programming as a guide, we analyse the BT principles of reactiveness and modularity in a formal framework of action selection. Proceeding from these principles, we review a number of challenging use cases of BTs in the literature, and show that reasoning via these principles leads to compatible solutions. Extending these arguments, we introduce a new class of control architectures we call generalised BTs or $k$-BTs and show how they can extend the applicability of BTs to some of the aforementioned challenging BT use cases while preserving the BT principles.

Related papers

• Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions [5.31484618181979]
  Behavior Tree (BT) is an appropriate control architecture for robots executing tasks following human instructions. This paper proposes a two-stage framework for BT generation, which first employs large language models to interpret goals from high-level instructions. We represent goals as well-formed formulas in first-order logic, effectively bridging intent understanding and optimal behavior planning.
  arXiv  Detail & Related papers  (2024-05-13T05:23:48Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• Levels of AGI for Operationalizing Progress on the Path to AGI [64.59151650272477]
  We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors. This framework introduces levels of AGI performance, generality, and autonomy, providing a common language to compare models, assess risks, and measure progress along the path to AGI.
  arXiv  Detail & Related papers  (2023-11-04T17:44:58Z)
• An Extended Convergence Result for Behaviour Tree Controllers [0.0]
  Behavior trees (BTs) are an optimally modular framework to assemble hierarchical hybrid control policies. We study the convergence of BTs, in the sense of reaching a desired part of the state space.
  arXiv  Detail & Related papers  (2023-08-17T14:05:45Z)
• Operationalising Responsible AI Using a Pattern-Oriented Approach: A Case Study on Chatbots in Financial Services [11.33499498841489]
  Responsible AI is the practice of developing and using AI systems in a way that benefits the humans, society, and environment. Various responsible AI principles have been released recently, but those principles are very abstract and not practical enough. To bridge the gap, we adopt a pattern-oriented approach and build a responsible AI pattern catalogue.
  arXiv  Detail & Related papers  (2023-01-03T23:11:03Z)
• Verifying Safety of Behaviour Trees in Event-B [0.0]
  Behavior Trees (BT) are becoming increasingly popular in the robotics community. We propose a formal specification of Behavior Trees and a methodology to prove invariants of already used trees.
  arXiv  Detail & Related papers  (2022-09-28T12:26:50Z)
• An expressiveness hierarchy of Behavior Trees and related architectures [0.0]
  We provide a formal framework for comparing the expressive power of Behavior Trees (BTs) to other action selection architectures. This leads us to an hierarchy of control architectures, which includes BTs, Decision Trees (DTs), Teleo-reactive Programs (TRs) and Finite State Machines (FSMs)
  arXiv  Detail & Related papers  (2021-04-16T06:46:52Z)
• BoxE: A Box Embedding Model for Knowledge Base Completion [53.57588201197374]
  Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB) Existing embedding models are subject to at least one of the following limitations. BoxE embeds entities as points, and relations as a set of hyper-rectangles (or boxes)
  arXiv  Detail & Related papers  (2020-07-13T09:40:49Z)
• Faithful Embeddings for Knowledge Base Queries [97.5904298152163]
  deductive closure of an ideal knowledge base (KB) contains exactly the logical queries that the KB can answer. In practice KBs are both incomplete and over-specified, failing to answer some queries that have real-world answers. We show that inserting this new QE module into a neural question-answering system leads to substantial improvements over the state-of-the-art.
  arXiv  Detail & Related papers  (2020-04-07T19:25:16Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)
• Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies [76.83991682238666]
  Branch and Bound (B&B) is the exact tree search method typically used to solve Mixed-Integer Linear Programming problems (MILPs) We propose a novel imitation learning framework, and introduce new input features and architectures to represent branching.
  arXiv  Detail & Related papers  (2020-02-12T17:43:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.