Goal Recognition in Latent Space

Amado, Leonardo; Pereira, Ramon Fraga; Aires, João Paulo; Magnaguagno, Maurício Cecílio; Granada, Roger; Meneguzzi, Felipe

doi:10.1109/ijcnn.2018.8489653

Cited by 37 publications

(42 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some examples of existing systems approaching the whole problem in a unified way are those relying on hierarchical probabilistic models (e.g., Saria and Mahadevan, 2004 ). Another direction that could lead to successful unified solutions could be to find suitable ways of combining logic-based and deep learning approaches in a way that the advantages of both worlds can be exploited, similar to what was done with logic-based and probabilistic approaches (some work in this direction has already been done, e.g., see Amado et al, 2018b ). These hybrid systems could be very good at dealing with sensory data while at the same time being very expressive at describing complete and complex plans.…”

Section: Discussionmentioning

confidence: 99%

“…In the case of activity recognition, recurrent neural networks have demonstrated to be very useful at classifying activities that are short in duration but have a natural ordering, thanks to their ability to take the context into account (Hammerla et al, 2016 ). Amado et al ( 2018a ) proposed the use of long short-term memory networks for a goal recognition task dealing with sensory input data, requiring much less manual introduction of domain knowledge than other state-of-the-art goal recognition approaches. Ordóñez and Roggen ( 2016 ) combined convolutional neural networks with long short-term memory networks for the task of activity recognition.…”

Section: Approaches To the Problem Of Activity Plan And Goal Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Activity, Plan, and Goal Recognition: A Review

Van-Horenbeke

Peer

2021

Front. Robot. AI

View full text Add to dashboard Cite

Recognizing the actions, plans, and goals of a person in an unconstrained environment is a key feature that future robotic systems will need in order to achieve a natural human-machine interaction. Indeed, we humans are constantly understanding and predicting the actions and goals of others, which allows us to interact in intuitive and safe ways. While action and plan recognition are tasks that humans perform naturally and with little effort, they are still an unresolved problem from the point of view of artificial intelligence. The immense variety of possible actions and plans that may be encountered in an unconstrained environment makes current approaches be far from human-like performance. In addition, while very different types of algorithms have been proposed to tackle the problem of activity, plan, and goal (intention) recognition, these tend to focus in only one part of the problem (e.g., action recognition), and techniques that address the problem as a whole have been not so thoroughly explored. This review is meant to provide a general view of the problem of activity, plan, and goal recognition as a whole. It presents a description of the problem, both from the human perspective and from the computational perspective, and proposes a classification of the main types of approaches that have been proposed to address it (logic-based, classical machine learning, deep learning, and brain-inspired), together with a description and comparison of the classes. This general view of the problem can help on the identification of research gaps, and may also provide inspiration for the development of new approaches that address the problem in a unified way.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Approaches To the Problem Of Activity Plan And Goal Recognitionmentioning

confidence: 99%

Activity, Plan, and Goal Recognition: A Review

Van-Horenbeke

Peer

2021

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…Pereira et al (2019) combine deep learning with planning techniques to recognize goals with continuous action spaces. Amado et al (2018) also use deep learning in an unsupervised fashion to lessen the need for domain expertise in goal recognition approaches; Polyvyanyy et al (2020) take a similar approach, but using process mining techniques. To learn these models, existing data of agents' behaviors is required to learn these models.…”

Section: Learned Goal Recognitionmentioning

confidence: 99%

Evaluation of Goal Recognition Systems on Unreliable Data and Uninspectable Agents

Rabkina

Kantharaju

Wilson

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Goal or intent recognition, where one agent recognizes the goals or intentions of another, can be a powerful tool for effective teamwork and improving interaction between agents. Such reasoning can be challenging to perform, however, because observations of an agent can be unreliable and, often, an agent does not have access to the reasoning processes and mental models of the other agent. Despite this difficulty, recent work has made great strides in addressing these challenges. In particular, two Artificial Intelligence (AI)-based approaches to goal recognition have recently been shown to perform well: goal recognition as planning, which reduces a goal recognition problem to the problem of plan generation; and Combinatory Categorical Grammars (CCGs), which treat goal recognition as a parsing problem. Additionally, new advances in cognitive science with respect to Theory of Mind reasoning have yielded an approach to goal recognition that leverages analogy in its decision making. However, there is still much unknown about the potential and limitations of these approaches, especially with respect to one another. Here, we present an extension of the analogical approach to a novel algorithm, Refinement via Analogy for Goal Reasoning (RAGeR). We compare RAGeR to two state-of-the-art approaches which use planning and CCGs for goal recognition, respectively, along two different axes: reliability of observations and inspectability of the other agent's mental model. Overall, we show that no approach dominates across all cases and discuss the relative strengths and weaknesses of these approaches. Scientists interested in goal recognition problems can use this knowledge as a guide to select the correct starting point for their specific domains and tasks.

show abstract

“…We then decode the recognized goal, obtaining its image representation using the decoder. We illustrate this process in Figure 1(c), and detail the process in Amado et al 2018.…”

Section: Goal Recognition In Latent Spacementioning

confidence: 99%

LatRec: Recognizing Goals in Latent Space (Student Abstract)

Amado

Meneguzzi

2020

AAAI

Self Cite

View full text Add to dashboard Cite

Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. Moving forward, we aim to develop a new data-driven goal recognition technique that infers the domain model using the same set of observations used in recognition itself.

show abstract

Goal Recognition in Latent Space

Cited by 37 publications

References 13 publications

Activity, Plan, and Goal Recognition: A Review

Activity, Plan, and Goal Recognition: A Review

Evaluation of Goal Recognition Systems on Unreliable Data and Uninspectable Agents

LatRec: Recognizing Goals in Latent Space (Student Abstract)

Contact Info

Product

Resources

About