Learning STRIPS Action Models with Classical Planning

Aineto, Diego; Jiménez, Sergio; Onaindía, Eva

doi:10.1609/icaps.v28i1.13870

Cited by 24 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A major benefit of learning such a safe action model is that any plan generated with the learned action model for any problem in the same domain is also valid with respect to the real, unknown, action model. Following prior works on learning action models (Amir and Chang 2008;Cresswell, McCluskey, and West 2013;Aineto, Jiménez, and Onaindia 2018) in general and safe action models in particular (Stern and Juba 2017;Juba, Le, and Stern 2021;Mordoch, Stern, and Juba 2023), we assume as input a set of observations of previously executed plans, represented as a set of trajectories. A trajectory T = ⟨s 0 , a 1 , s 1 , .…”

Section: Preliminariesmentioning

confidence: 99%

Safe Learning of PDDL Domains with Conditional Effects

Mordoch,

Scala,

Stern

et al. 2024

ICAPS

View full text Add to dashboard Cite

Powerful domain-independent planners have been developed to solve various types of planning problems. These planners often require a model of the acting agent's actions, given in some planning domain description language. Manually designing such an action model is a notoriously challenging task. An alternative is to automatically learn action models from observation. Such an action model is called safe if every plan created with it is consistent with the real, unknown action model. Algorithms for learning such safe action models exist, yet they cannot handle domains with conditional or universal effects, which are common constructs in many planning problems. We prove that learning non-trivial safe action models with conditional effects may require an exponential number of samples. Then, we identify reasonable assumptions under which such learning is tractable and propose Conditional-SAM, the first algorithm capable of doing so. We analyze Conditional-SAM theoretically and evaluate it experimentally. Our results show that the action models learned by Conditional-SAM can be used to solve perfectly most of the test set problems in most of the experimented domains.

show abstract

Section: Preliminariesmentioning

confidence: 99%

Safe Learning of PDDL Domains with Conditional Effects

Mordoch,

Scala,

Stern

et al. 2024

ICAPS

View full text Add to dashboard Cite

show abstract

“…The states in the TSs are composed of Boolean propositions to denote the current planning phase. STRIPS has been successfully applied to numerous tasks (Bylander, 1994;Jiménez et al, 2012) and updated over the years (Garrett et al, 2017;Aineto et al, 2018). Yet, it is challenging to apply STRIPS to applications that involve conditional actions.…”

Section: Task and Motion Planningmentioning

confidence: 99%

SpaTiaL: Monitoring and Planning of Robotic Tasks Using Spatio-Temporal Logic Specifications

Pek

Schuppe

Esposito

et al. 2023

Preprint

View full text Add to dashboard Cite

Many tasks require robots to manipulate objects while satisfying a complex interplay of spatial and temporal constraints. For instance, a table setting robot first needs to place a mug and then fill it with coffee, while satisfying spatial relations such as forks need to placed left of plates. Existing solutions are often not robot-agnostic, not expressive enough to monitor and plan complex tasks, and require users to manually define object relations. We propose the spatio-temporal framework SpaTiaL that unifies the specification, monitoring, and planning of object-centric robotic tasks. SpaTiaL captures diverse spatial relations between objects and temporal task patterns. Our experiments with recorded data, simulations, and robots demonstrate how SpaTiaL provides real-time monitoring and facilitates online planning. SpaTiaL is open source and easily expandable to new object relations and robotic applications.

show abstract

Section: Related Workmentioning

confidence: 99%

SpaTiaL: monitoring and planning of robotic tasks using spatio-temporal logic specifications

Pek,

Schuppe,

Esposito

et al. 2023

Auton Robot

View full text Add to dashboard Cite

Many tasks require robots to manipulate objects while satisfying a complex interplay of spatial and temporal constraints. For instance, a table setting robot first needs to place a mug and then fill it with coffee, while satisfying spatial relations such as forks need to placed left of plates. We propose the spatio-temporal framework SpaTiaL that unifies the specification, monitoring, and planning of object-oriented robotic tasks in a robot-agnostic fashion. SpaTiaL is able to specify diverse spatial relations between objects and temporal task patterns. Our experiments with recorded data, simulations, and real robots demonstrate how SpaTiaL provides real-time monitoring and facilitates online planning. SpaTiaL is open source and easily expandable to new object relations and robotic applications.

show abstract

Learning STRIPS Action Models with Classical Planning

Cited by 24 publications

References 18 publications

Safe Learning of PDDL Domains with Conditional Effects

Safe Learning of PDDL Domains with Conditional Effects

SpaTiaL: Monitoring and Planning of Robotic Tasks Using Spatio-Temporal Logic Specifications

SpaTiaL: monitoring and planning of robotic tasks using spatio-temporal logic specifications

Contact Info

Product

Resources

About