Explaining robot actions

By M. Lomas, R. Chevalier, E. Cross, Robert Christopher Garrett, J. Hoare, Michael Kopack. 2012

87 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Social Psychology, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Social Psychology

In Reinforcement Learning

Citations in the corpus

Measuring and Improving BERT’s Mathematical Abilities by Predicting the Order of Reasoning. (2021, background): “Symbolic or semi-symbolic architectures naturally produce justiﬁcations as a sequence of formulas in some formal language (Lane et al., 2005; Core et al., 2006; Lomas et al., 2012; Johnson; Liang, 2016; Malinowski and Fritz, 2014).”
Generating Visual Explanations (2016, background): “In contrast to systems like [13,14,15,16,17,18] which aim to explain the underlying mechanism behind a decision, authors in [1] concentrate on why a prediction is justiﬁable to a user.”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “…2016; Johnson, 1994; Kim, Chacha, and Shah, 2013; Lane, Core, Van Lent, Solomon, and Gomboc, 2005; Langley, Meadows, Sridharan, and Choi, 2017; Lomas et al., 2012; Metoyer et al., 2010; Mnih et al., 2015; Moulin et al., 2002; Rosenthal, Selvaraj, and Veloso, 2016; S. Singh, Lewis, Barto, and…”
Understanding the Origins of Bias in Word Embeddings (2018, background): “Other eﬀorts to increase the explainability of machine learning models have largely focused on providing visual or textual information to the user as justiﬁcation for classiﬁcation or reinforcement learning decisions [17, 9, 13].”
Attentive Explanations: Justifying Decisions and Pointing to the Evidence (2016, background): “ion are mostly template based. [39] proposes explanation systems for medical applications, [24, 40, 10] propose explanations as a feedback to improve simulated training for special teaching programs, [28] proposes a model to explain robot actions, [23] evaluates methods developed to explain Bayesian”
Situation Awareness-Based Agent Transparency (2014, unknown): “Lomas and Chevalier (2012) developed a projection system where a robotic entity was able to respond to questions asked to it in terms of understandable reasoning/projections of future state.”
Combinatorial Methods for Explainable AI (2020, background): “Consequently, there is a significant need for improvements in explainability of AI/ML system functions and decisions [1][2][3][4][5][6][7].”
Explainable Agents and Robots: Results from a Systematic Literature Review (2019, background): “Trust [102] [58] [49] [100] [59] [29] [67] [6] [99] [52] [57] [27] [7] [42] [104] [31] [14] [65] [43] [62] [46] [29] [96]”
Ethics of artificial intelligence and robotics (2020, background): “There are several technical activities that aim at ‘explainable AI’, starting with (Van Lent, Fisher, and Mancuso 1999; Lomas et al. 2012) and, more recently, a DARPA programme (Gunning 2018) and the AI4EU project on ‘human-centred AI’.”
How People Explain Action (and Autonomous Intelligent Systems Should Too) (2017, background): “When a robot fails to communicate its intentions, people not only perceive that robot as creepy or un-settling (Williams, Briggs, and Scheutz 2015) they also perceive such robots as erratic and untrustworthy even when they follow a clear decision-making process (Lomas et al. 2012).”