Synthesis of correct-by-construction behavior trees

Colledanchise, Michele; Murray, Richard M.; Ögren, Petter

doi:10.1109/iros.2017.8206502

Cited by 41 publications

(18 citation statements)

References 20 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [21] the action capabilities of a NAO robot tasked with grasping and transporting objects were modeled as a transition system and the goal as a State-Event Linear Temporal Logic (LTL) formula. LTL is also used in [22] to synthesize a BT for a maze navigation task. The rigorous and complex formulations of the LTL formula make the approach scale poorly for more complicated tasks or less predictable environments.…”

Section: Related Workmentioning

confidence: 99%

Combining Planning and Learning of Behavior Trees for Robotic Assembly

Styrud¹,

Iovino²,

Norrlöf³

et al. 2021

Preprint

View full text Add to dashboard Cite

Industrial robots can solve very complex tasks in controlled environments, but modern applications require robots able to operate in unpredictable surroundings as well. An increasingly popular reactive policy architecture in robotics is Behavior Trees but as with other architectures, programming time still drives cost and limits flexibility. There are two main branches of algorithms to generate policies automatically, automated planning and machine learning, both with their own drawbacks. We propose a method for generating Behavior Trees using a Genetic Programming algorithm and combining the two branches by taking the result of an automated planner and inserting it into the population. Experimental results confirm that the proposed method of combining planning and learning performs well on a variety of robotic assembly problems and outperforms both of the base methods used separately. We also show that this type of high level learning of Behavior Trees can be transferred to a real system without further training.

show abstract

Section: Related Workmentioning

confidence: 99%

Combining Planning and Learning of Behavior Trees for Robotic Assembly

Styrud¹,

Iovino²,

Norrlöf³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the actual interface with robot functions are not modeled. Operational models such as Behavior Trees have also been used as a basic model for deliberation, using synthesis from a LTL formulation [15], or hierarchical planning using an HTN-like process [16]. The same LTL-based synthesis has been applied to Finite State Machines in [17].…”

Section: Formalization Of Robot Skills With Descriptive and Operational Modelsmentioning

confidence: 99%

Formalization of Robot Skills with Descriptive and Operational Models

Lesire

Doose

Grand

2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

“…There are works providing formal semantics of BTs using either description logic [24], non-linear algebra [25], and pseudocodes [26]; some authors proposed a framework Michele Colledanchise, Daniele E. Domenichelli, and Lorenzo Natale are with Istituto Italiano di Tecnologia, via Morego 30, 16163 Genova. (name.surname@iit.it) Giuseppe Cicala and Armando Tacchella are with Università degli Studi di Genova, DIBRIS (name.surname@unige.it) to synthesize BTs that satisfy specifications in Linear Temporal Logic (LTL) [27], [28], and others [29] use LTL to specify the semantics of BT nodes and their composition. However, we argue that these works do not address the problems of (i) embedding BTs in a context including other elements of the software architecture that are required for the BT execution and (ii) verifying that the stated requirements are fulfilled in such context.…”

Section: Introductionmentioning

confidence: 99%

Formalizing the Execution Context of Behavior Trees for Runtime Verification of Deliberative Policies

Colledanchise,

Cicala,

Domenichelli

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Our research aims to enable automated property verification of deliberative components in robot control architectures. We focus on a formalization of the execution context of Behavior Trees (BTs) to provide a scalable, yet formally grounded, methodology to enable runtime verification and prevent unexpected robot behaviors to hamper deployment. To this end, we consider a message-passing model that accommodates both synchronous and asynchronous composition of parallel components, in which BTs and other components execute and interact according to the communication patterns commonly adopted in robotic software architectures. We introduce a formal property specification language to encode requirements and build runtime monitors. We performed a set of experiments both on simulations and on the real robot, demonstrating the feasibility of our approach in a realistic application, and its integration in a typical robot software architecture. We also provide an OS-level virtualization environment to reproduce the experiments in the simulated scenario.

show abstract

Synthesis of correct-by-construction behavior trees

Cited by 41 publications

References 20 publications

Combining Planning and Learning of Behavior Trees for Robotic Assembly

Combining Planning and Learning of Behavior Trees for Robotic Assembly

Formalization of Robot Skills with Descriptive and Operational Models

Formalizing the Execution Context of Behavior Trees for Runtime Verification of Deliberative Policies

Contact Info

Product

Resources

About