Extending the JADE Agent Behaviour Model with JBehaviourTrees Framework

Bojić, Iva; Lipić, Tomislav; Kušek, Mario; Jezic, Gordan

doi:10.1007/978-3-642-22000-5_18

Cited by 19 publications

(19 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantage of BTs as compared to FSMs was also the reason for extending the JADE agent Behavior Model with BTs in [10], and the benefits of using BTs to control complex multi mission UAVs was described in [11].…”

Section: Introductionmentioning

confidence: 99%

How Behavior Trees Modularize Hybrid Control Systems and Generalize Sequential Behavior Compositions, the Subsumption Architecture, and Decision Trees

2017

View full text Add to dashboard Cite

Abstract-Behavior Trees (BTs) is a way of organizing the switching structure of a Hybrid Dynamical System (HDS), that was originally introduced in the computer game programming community.In this paper, we analyze how the BT representation increases the modularity of a HDS, and how key system properties are preserved over compositions of such systems, in terms of combining two BTs into a larger one. We also show how BTs can be seen as a generalization of Sequential Behavior Compositions, the Subsumption Architecture and Decisions Trees. These three tools are powerful, but quite different, and the fact that they are unified in a natural way in BTs might be a reason for their popularity in the gaming community. We conclude the paper by giving a set of examples illustrating how the proposed analysis tools can be applied to robot control BTs.

show abstract

Section: Introductionmentioning

confidence: 99%

How Behavior Trees Modularize Hybrid Control Systems and Generalize Sequential Behavior Compositions, the Subsumption Architecture, and Decision Trees

2017

View full text Add to dashboard Cite

show abstract

“…(32) The probability vector, according to (6), is given by: π(t) = π 1 (t) π 2 (t) π 3 (t) π 4 (t) π 5 (t) π 6 (t) π 7 (t) (33) We can now derive closed form expression for MTTS and MTTF. Using the decomposition in (18), the matrices computed according Equations 21 and 20 are:…”

Section: Resultsmentioning

confidence: 99%

“…Given the infinitesimal generator matrix Q(t), we compute the probability distribution over time of the node according to (6) with the initial condition π 0 = [1 0] that represents the state in which none of the children have returned success/failure yet.…”

Section: Probability Distribution Over Timementioning

confidence: 99%

“…The advantage of BTs as compared to FSMs was also the reason for extending the JADE agent Behavior Model with BTs in [6], and the benefits of using BTs to control complex multi mission Unmanned Aircraft Vehicle (UAVs) was described in [7]. The modularity and structure of BTs enabled a step towards the formal verification of mission plans in [9].…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Performance analysis of stochastic behavior trees

Colledanchise

Marzinotto

Ögren

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

This paper presents a mathematical framework for performance analysis of Behavior Trees (BTs). BTs are a recent alternative to Finite State Machines (FSMs), for doing modular task switching in robot control architectures. By encoding the switching logic in a tree structure, instead of distributing it in the states of a FSM, modularity and reusability are improved.In this paper, we compute performance measures, such as success/failure probabilities and execution times, for plans encoded and executed by BTs. To do this, we first introduce Stochastic Behavior Trees (SBT), where we assume that the probabilistic performance measures of the basic action controllers are given. We then show how Discrete Time Markov Chains (DTMC) can be used to aggregate these measures from one level of the tree to the next. The recursive structure of the tree then enables us to step by step propagate such estimates from the leaves (basic action controllers) to the root (complete task execution). Finally, we verify our analytical results using massive Monte Carlo simulations, and provide an illustrative example of the results for a complex robotic task.

show abstract

“…BTs is a way to encode a HDS that replaces the explicitly listed state transition functions of classic HDS with transitions that are implicitly given by a tree structure, see details below, and in references. 6,7,[14][15][16] Thus, a given BT can be inserted as a subtree anywhere in any other BT and still be perfectly valid, and the transitions between the new and old parts of the combined tree will be implicitly given by the combined tree structure. Similarly, any part of a BT can be removed, as long as the remaining tree is connected, without causing invalid transitions.…”

Section: Introductionmentioning

confidence: 99%

Increasing Modularity of UAV Control Systems using Computer Game Behavior Trees

Ögren

2012

AIAA Guidance, Navigation, and Control Conference

100

View full text Add to dashboard Cite

In this paper, we argue that the modularity, reusability and complexity of Unmanned Aerial Vehicle (UAV) guidance and control systems might be improved by using a Behavior Tree (BT) architecture. BTs are a particular kind of Hybrid Dynamical Systems (HDS), where the state transitions of the HDS are implicitly encoded in a tree structure, instead of explicitly stated in transition maps. In the gaming industry, BTs have gained a lot of interest, and are now replacing HDS in the control architecture of many automated in-game opponents. Below, we explore the relationship between HDS and BTs. We show that any HDS can be written as a BT and that many common UAV control constructs are quite naturally formulated as BTs. Finally, we discuss the positive implications of making the above mentioned state transitions implicit in the BTs.

show abstract

Extending the JADE Agent Behaviour Model with JBehaviourTrees Framework

Cited by 19 publications

References 7 publications

How Behavior Trees Modularize Hybrid Control Systems and Generalize Sequential Behavior Compositions, the Subsumption Architecture, and Decision Trees

How Behavior Trees Modularize Hybrid Control Systems and Generalize Sequential Behavior Compositions, the Subsumption Architecture, and Decision Trees

Performance analysis of stochastic behavior trees

Increasing Modularity of UAV Control Systems using Computer Game Behavior Trees

Contact Info

Product

Resources

About