Explainable Planning

Fox, Maria; Long, Derek; Magazzeni, Daniele

doi:10.48550/arxiv.1709.10256

Cited by 23 publications

(29 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While a utility function may be made up of dozens of variables, RGA selects only the top k factors, which are then used to generate a human-readable rationale. Note that [14] has shown that in the context of an explainable planner, generating justifications to explain both good and bad action choices leads to a more robust explainable system. Motivated r.append(genNeg( f .name, a))…”

Section: Rationale Generating Algorithmmentioning

confidence: 99%

Leveraging rationales to improve human task performance

Das

Chernova

2020

Proceedings of the 25th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Machine learning (ML) systems across many application areas are increasingly demonstrating performance that is beyond that of humans. In response to the proliferation of such models, the field of Explainable AI (XAI) has sought to develop techniques that enhance the transparency and interpretability of machine learning methods. In this work, we consider a question not previously explored within the XAI and ML communities: Given a computational system whose performance exceeds that of its human user, can explainable AI capabilities be leveraged to improve the performance of the human?We study this question in the context of the game of Chess, for which computational game engines that surpass the performance of the average player are widely available. We introduce the Rationale-Generating Algorithm, an automated technique for generating rationales for utility-based computational methods, which we evaluate with a multi-day user study against two baselines. The results show that our approach produces rationales that lead to statistically significant improvement in human task performance, demonstrating that rationales automatically generated from an AI's internal task model can be used not only to explain what the system is doing, but also to instruct the user and ultimately improve their task performance. CCS CONCEPTS• Human-centered computing → Interaction paradigms.

show abstract

Section: Rationale Generating Algorithmmentioning

confidence: 99%

Leveraging rationales to improve human task performance

Das

Chernova

2020

Proceedings of the 25th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

show abstract

“…AIX360 [1]). Interactive tools also exist [10,6,7,28], but: 1) they do not consider to offer descriptive explanations, but other types of explanations on pre-defined aspects of the ADM; 2) or they generate explanations automatically (e.g from static argumentation frameworks), using templates. Completely automated sense-making or understanding articulation is possible only with very specific ADMs, or by pre-defining narrative scenarios that can be as powerful as dangerous [3,25].…”

Section: Related Workmentioning

confidence: 99%

Modelling GDPR-Compliant Explanations for Trustworthy AI

Sovrano¹,

Vitali²,

Palmirani³

2020

Electronic Government and the Information Systems Perspective

View full text Add to dashboard Cite

Through the General Data Protection Regulation (GDPR), the European Union has set out its vision for Automated Decision-Making (ADM) and AI, which must be reliable and human-centred. In particular we are interested on the Right to Explanation, that requires industry to produce explanations of ADM. The High-Level Expert Group on Artificial Intelligence (AI-HLEG), set up to support the implementation of this vision, has produced guidelines discussing the types of explanations that are appropriate for user-centred (interactive) Explanatory Tools. In this paper we propose our version of Explanatory Narratives (EN), based on user-centred concepts drawn from ISO 9241, as a model for user-centred explanations aligned with the GDPR and the AI-HLEG guidelines. Through the use of ENs we convert the problem of generating explanations for ADM into the identification of an appropriate path over an Explanatory Space, allowing explainees to interactively explore it and produce the explanation best suited to their needs. To this end we list suitable exploration heuristics, we study the properties and structure of explanations, and discuss the proposed model identifying its weaknesses and strengths.

show abstract

“…This interpretation model of the human enables the AI agent to infer about the human's expectation of itself. Using such a model, an agent can generate legible motions [14], explicable plans [9], [15], [16], or assistive actions [17]. In these approaches, the AI agent substitutes cost with a new metric that simultaneously considers cost and a distance measure between the robot's behavior and the human's expectation.…”

Section: Related Workmentioning

confidence: 99%

Online Explanation Generation for Human-Robot Teaming

Zakershahrak,

Gong,

Sadassivam

et al. 2019

Preprint

View full text Add to dashboard Cite

As AI becomes an integral part of our lives, the development of explainable AI, embodied in the decisionmaking process of an AI or robotic agent, becomes imperative. For a robotic teammate, the ability to generate explanations to explain its behavior is one of the key requirements of explainable agency. Prior work on explanation generation focuses on supporting the rationale behind the robot's decision (or behavior). These approaches, however, fail to consider the mental workload needed to understand the received explanation. In other words, the human teammate is expected to understand any explanation provided no matter how much information is presented. In this work, we argue that explanations, especially ones of a complex nature, should be made in an online fashion during the execution, which helps spread out the information to be explained and thus reduce the mental workload of humans in highly demanding tasks. However, a challenge here is that the different parts of an explanation may be dependent on each other, which must be taken into account when generating online explanations. To this end, a general formulation of online explanation generation is presented with three variations satisfying different properties. The new explanation generation methods are based on a model reconciliation setting introduced in our prior work. We evaluate our methods both with human subjects in a standard planning competition (IPC) domain, using NASA Task Load Index (TLX), as well as in simulation with ten different problems across two IPC domains. Results strongly suggest that our methods not only generate explanations that are perceived as less cognitively demanding and much preferred over the baselines but also are computationally efficient.

show abstract

Explainable Planning

Cited by 23 publications

References 0 publications

Leveraging rationales to improve human task performance

Leveraging rationales to improve human task performance

Modelling GDPR-Compliant Explanations for Trustworthy AI

Online Explanation Generation for Human-Robot Teaming

Contact Info

Product

Resources

About