Learning Combinatory Categorial Grammars for Plan Recognition

Geib, Christopher W.; Kantharaju, Pavan

doi:10.1609/aaai.v32i1.11729

Cited by 7 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors introduce a hierarchical planning system based on a model defined as Combinatory Categorial Grammar (Steedman, 2000), a formalism lent from natural language processing. Similar representations have been applied before in the field of plan and goal recognition (Geib, 2009;Geib & Goldman, 2009, 2011 and there are also approaches in the literature on how to learn them (Geib & Kantharaju, 2018). One motivation of Geib and Weerasinghe's work is to have a learnable, unified representation for natural language processing, plan and goal recognition, and planning.…”

Section: Related Workmentioning

confidence: 97%

See 1 more Smart Citation

The TOAD System for Totally Ordered HTN Planning

Höller

2024

jair

View full text Add to dashboard Cite

We present an approach for translating Totally Ordered Hierarchical Task Network (HTN) planning problems to classical planning problems. While this enables the use of sophisticated classical planning systems to find solutions, we need to overcome the differences in expressiveness of these two planning formalisms. Prior work on this topic did this by translating bounded HTN problems. In contrast, we approximate them, i.e., we change the problem such that every action sequence that is a solution to the HTN problem is also a solution for the classical problem, but the latter might have more solutions. To obtain a sound overall approach, we verify solutions returned by the classical planning system to ensure that they are also solutions to the HTN problem. For translation and approximation, we use techniques introduced to approximate Context-Free Languages by using Finite Automata. We named our system Toad (Totally Ordered HTN Approximation using DFA). For a subset of HTN problems the translation is even possible without approximation. Whether or not it is necessary is decided based on the property of self-embedding, which comes also from the field of formal languages. We investigate the theoretical connection of self-embedding and tail-recursiveness, a property from the HTN literature used to identify a subclass of HTN planning problems that can be translated to classical planning, and show that it is more general. To guide the classical planner, we introduce a novel heuristic tailored towards our models. We evaluate Toad on the benchmark set of the 2020 International Planning Competition. Our evaluation shows that (1) most problems can be translated without approximation and that (2) Toad is competitive with the state of the art in HTN planning.

show abstract

Section: Related Workmentioning

confidence: 97%

“…Another approach on hierarchical planning, though not directly on HTN planning, has been presented by Geib and Weerasinghe (2020). The authors introduce a hierarchical planning system based on a model defined as Combinatory Categorial Grammar (Steedman, 2000), a formalism lent from natural language processing.…”

Section: Related Workmentioning

confidence: 99%

The TOAD System for Totally Ordered HTN Planning

Höller

2024

jair

View full text Add to dashboard Cite

show abstract

“…Previous work in goal and plan recognition has typically relied on rich domain knowledge (e.g., Kautz and Allen 1986;Ramírez and Geffner 2011), thus limiting the applicability of this body of work. To leverage the existence of large datasets and machine learning techniques, some approaches to goal recognition eschew assumptions about domain knowledge and instead propose to learn models from data and use these models to predict an agent's goal given a sequence of observations (e.g., Geib and Kantharaju 2018;Amado et al 2018;Polyvyanyy et al 2020). Such approaches either learn models of the dynamics that govern the environment which are then used in goal recognition, or directly learn classifiers that are given a sequence of observations and predict the goal.…”

Section: Related Workmentioning

confidence: 99%

Interpretable Sequence Classification via Discrete Optimization

Shvo

Icarte

et al. 2021

AAAI

View full text Add to dashboard Cite

Sequence classification is the task of predicting a class label given a sequence of observations. In many applications such as healthcare monitoring or intrusion detection, early classification is crucial to prompt intervention. In this work, we learn sequence classifiers that favour early classification from an evolving observation trace. While many state-of-the-art sequence classifiers are neural networks, and in particular LSTMs, our classifiers take the form of finite state automata and are learned via discrete optimization. Our automata-based classifiers are interpretable---supporting explanation, counterfactual reasoning, and human-in-the-loop modification---and have strong empirical performance. Experiments over a suite of goal recognition and behaviour classification datasets show our learned automata-based classifiers to have comparable test performance to LSTM-based classifiers, with the added advantage of being interpretable.

show abstract

“…Its aim is to infer the top-level goal of an agent based on input observation sequences and output an explanation of the observation sequence [1]. Currently, goal recognition has been applied in various fields, including intelligent assistants [2,3], autonomous driving [4,5], robot navigation [6,7], military confrontation [8], and more [9]. For example, in the application of goal recognition in a smart home assistant [2,3], the input observation sequence consists of a series of actions performed by a person as observed by a camera.…”

Section: Introductionmentioning

confidence: 99%

“…Currently, goal recognition has been applied in various fields, including intelligent assistants [2,3], autonomous driving [4,5], robot navigation [6,7], military confrontation [8], and more [9]. For example, in the application of goal recognition in a smart home assistant [2,3], the input observation sequence consists of a series of actions performed by a person as observed by a camera. By using a goal recognition algorithm, the system can, for example, identify the goal of an elderly person as needing to go to the kitchen.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Online Goal Recognition in Continuous Domains via Deep Reinforcement Learning

Fang,

Chen,

Zeng

et al. 2023

Entropy

View full text Add to dashboard Cite

The problem of goal recognition involves inferring the high-level task goals of an agent based on observations of its behavior in an environment. Current methods for achieving this task rely on offline comparison inference of observed behavior in discrete environments, which presents several challenges. First, accurately modeling the behavior of the observed agent requires significant computational resources. Second, continuous simulation environments cannot be accurately recognized using existing methods. Finally, real-time computing power is required to infer the likelihood of each potential goal. In this paper, we propose an advanced and efficient real-time online goal recognition algorithm based on deep reinforcement learning in continuous domains. By leveraging the offline modeling of the observed agent’s behavior with deep reinforcement learning, our algorithm achieves real-time goal recognition. We evaluate the algorithm’s online goal recognition accuracy and stability in continuous simulation environments under communication constraints.

show abstract

Learning Combinatory Categorial Grammars for Plan Recognition

Cited by 7 publications

References 12 publications

The TOAD System for Totally Ordered HTN Planning

The TOAD System for Totally Ordered HTN Planning

Interpretable Sequence Classification via Discrete Optimization

Real-Time Online Goal Recognition in Continuous Domains via Deep Reinforcement Learning

Contact Info

Product

Resources

About