– D3WA+ – A Case Study of XAIP in a Model Acquisition Task for Dialogue Planning

Sreedharan, Sarath; Chakraborti, Tathagata; Muise, Christian; Khazaeni, Yasaman; Kambhampati, Subbarao

doi:10.1609/icaps.v30i1.6744

Cited by 13 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model reconciliation (Chakraborti et al 2019;Sreedharan et al 2019) states that the role of an explanation technique is to bridge the gap between model and user's perception of such model by providing the user with knowledge that might be missing. Model Acquisition (Sreedharan et al 2020) aims to move the actual model (revealed model) towards an ideal model intended by the designer (mental model).…”

Section: Related Work Ai Planning Explanationsmentioning

confidence: 99%

Actor-Focused Interactive Visualization for AI Planning

Cantareira

Canal

Borgo

2022

ICAPS

View full text Add to dashboard Cite

As we grow more reliant on AI systems for an increasing variety of applications in our lives, the need to understand and interpret such systems also becomes more pronounced, be it for improvement, trust, or legal liability. AI Planning is one type of task that provides explanation challenges, particularly due to the increasing complexity in generated plans and convoluted causal chains that connect actions and determine overall plan structure. While there are many recent techniques to support plan explanation, visual aids for navigating this data are quite limited. Furthermore, there is often a barrier between techniques focused on abstract planning concepts and domain-related explanations. In this paper, we present a visual analytics tool to support plan summarization and interaction, focusing in robotics domains using an actor-based structure. We show how users can quickly grasp vital information about actions involved in a plan and how they relate to each other. Finally, we present a framework used to design our tool, highlighting how general PDDL elements can be converted into visual representations and further connecting concept to domain.

show abstract

Section: Related Work Ai Planning Explanationsmentioning

confidence: 99%

Actor-Focused Interactive Visualization for AI Planning

Cantareira

Canal

Borgo

2022

ICAPS

View full text Add to dashboard Cite

show abstract

“…In the original work, the space of excuses was confined to initial state changes only, as described above in Definition 4. Since then, the notion of excuses was extended to generic revision of planning tasks [34], and several works have used it as a means to debug planning models in domain authoring tasks such as goal-oriented conversational agents, decision support systems, intelligent tutoring systems [35][36][37].…”

Section: The Guided Demonstration Taskmentioning

confidence: 99%

Automated Generation of Robotic Planning Domains from Observations

Diehl

Paxton

Ramirez-Amaro

2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Automated planning enables robots to find plans to achieve complex, long-horizon tasks, given a planning domain. This planning domain consists of a list of actions, with their associated preconditions and effects, and is usually manually defined by a human expert, which is very timeconsuming or even infeasible. In this paper, we introduce a novel method for generating this domain automatically from human demonstrations. First, we automatically segment and recognize the different observed actions from human demonstrations. From these demonstrations, the relevant preconditions and effects are obtained, and the associated planning operators are generated. Finally, a sequence of actions that satisfies a user-defined goal can be planned using a symbolic planner. The generated plan is executed in a simulated environment by the TIAGo robot. We tested our method on a dataset of 12 demonstrations collected from three different participants. The results show that our method is able to generate executable plans from using one single demonstration with a 92% success rate, and 100% when the information from all demonstrations are included, even for previously unknown stacking goals.

show abstract

“…In [27], authors introduced a vocabulary for triaging composed processes iteratively through a mixture of foils, landmarks (i.e. necessary steps), and abstractions.…”

Section: Interpretability and Authoring Toolsmentioning

confidence: 99%

Applications of Automated Planning for Business Process Management

Marrella

Chakraborti²

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This is a brief summary of the applications of automated planning in the field of Business Process Management (BPM); and accompanies a tutorial with the same theme at the 19th International Conference on Business Process Management (BPM 2021). We hope that this report is able to quickly onboard newcomers into this field with a broad overview of the associated challenges and opportunities, as well as provide established practitioners in the field some new food for thought in terms of the state-of-the-art and the evolving nature of these problems.

show abstract

– D3WA+ – A Case Study of XAIP in a Model Acquisition Task for Dialogue Planning

Cited by 13 publications

References 23 publications

Actor-Focused Interactive Visualization for AI Planning

Actor-Focused Interactive Visualization for AI Planning

Automated Generation of Robotic Planning Domains from Observations

Applications of Automated Planning for Business Process Management

Contact Info

Product

Resources

About