Automatic Safe Behaviour Tree Synthesis for Autonomous Agents

Tadewos, Tadewos G.; Shamgah, Laya; Karimoddini, Ali

doi:10.1109/cdc40024.2019.9030183

Cited by 14 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By equipping these ANs with the edge computing capability, a suite of innovative computation tools can be realized in SD-VEC to bolster ultra-low latency networking, including automatic task allocations between edge ANs and the cloud, anticipatory mobility management, and data analytic assisting predictive safety and real-time actions. Our preliminary results on online automatic tasking can be adopted for safe coordination of actions taking into account the operation cost and time of the actions and scenarios for commutation network management and traffic control [8].…”

Section: Software-defined Vehicular Computingmentioning

confidence: 99%

SD-VEC: Software-Defined Vehicular Edge Computing with Ultra-Low Latency

Lin¹,

Chen²,

Karimoddini³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

New paradigm shifts and 6G technological revolution in vehicular services have emerged toward unmanned driving, automated transportation, and self-driving vehicles. As the technology for autonomous vehicles becomes mature, real challenges come from reliable, safe, real-time connected transportation operations to achieve ubiquitous and prompt information exchanges with massive connected and autonomous vehicles. This article aims at introducing novel wireless distributed architectures that embed the edge computing capability inside software-defined vehicular networking infrastructure. Such edge networks consist of open-loop grant-free communications and computing-based control frameworks, which enable dynamic eco-routing with ultra-low latency and mobile data-driven orchestration. Thus, this work advances the frontiers of machine learning potentials and next-generation mobile system realization in vehicular networking applications.

show abstract

Section: Software-defined Vehicular Computingmentioning

confidence: 99%

SD-VEC: Software-Defined Vehicular Edge Computing with Ultra-Low Latency

Lin¹,

Chen²,

Karimoddini³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…[87] LTL [164], [100], [25], [88] GOAP [146] Other [159], [160], [182] [126] previously encountered. Following this process, rules can be constructed that may solve future problems by retrieving and reusing stored behaviors [46,119].…”

Section: Plannermentioning

confidence: 99%

Section: Planning and Analytic Designmentioning

confidence: 99%

“…Based on the same idea, [159] and [160] present their own algorithm for the automatic synthesis of BTs. This algorithm is combined with dynamic differential logic (DL), a verification tool used in [159] to ensure the safety of the generated BT. Then, DL is combined with a market-based auction algorithm and a coordinator to assign specific task to certain robots, in the multisystem scenario presented in [160].…”

Section: Planning and Analytic Designmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Behavior Trees in Robotics and AI

Iovino¹,

Scukins²,

Styrud³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Along the same lines, other work [4], [17], [18] explores different ways of synthesizing a BT using a planner. Automatic synthesis is employed to produce BTs with guaranteed performance [19] or safety [20]. Other approaches extend BTs by integrating models where domain knowledge can be learned automatically, for instance using reinforcement learning [21], [22], genetic programming [23], or imitation learning [24].…”

Section: Related Workmentioning

confidence: 99%

Reconfigurable Behavior Trees: Towards an Executive Framework Meeting High-level Decision Making and Control Layer Features

Cruz¹,

Piater²,

Saveriano³

2020

Preprint

View full text Add to dashboard Cite

Behavior Trees (BTs) constitute a widespread artificial intelligence tool that has been successfully adopted in robotics. Their advantages include simplicity, modularity, and reusability of code. However, Behavior Trees remain a highlevel decision making engine; control features cannot easily be integrated. This paper proposes Reconfigurable Behavior Trees (RBTs), an extension of the traditional BTs that incorporates sensed information coming from the robotic environment in the decision making process. We endow RBTs with continuous sensory data that permits the online monitoring of the task execution. The resulting stimulus-driven architecture is capable of dynamically handling changes in the executive context while keeping the execution time low. The proposed framework is evaluated on a set of robotic experiments. The results show that RBTs are a promising approach for robotic task representation, monitoring, and execution.

show abstract

Automatic Safe Behaviour Tree Synthesis for Autonomous Agents

Cited by 14 publications

References 17 publications

SD-VEC: Software-Defined Vehicular Edge Computing with Ultra-Low Latency

SD-VEC: Software-Defined Vehicular Edge Computing with Ultra-Low Latency

A Survey of Behavior Trees in Robotics and AI

Reconfigurable Behavior Trees: Towards an Executive Framework Meeting High-level Decision Making and Control Layer Features

Contact Info

Product

Resources

About