Frank Foerster

Dr. Frank Foerster

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2023 in Frontiers in Robotics and AI
Verified
Journal Article
Open access
FFFrank Foerster
Frank Foerster
MRMarta Romeo
Marta Romeo
PHPatrick Holthaus
Patrick Holthaus
LWLuke J. Wood
Luke J. Wood
CDChristian Dondrup
Christian Dondrup
EKEpaminondas Kapetanios
Epaminondas Kapetanios
This paper summarizes the structure and findings from the first Workshop on Troubles and Failures in Conversations between Humans and Robots. The workshop was organized to bring together a small, interdisciplinary group of researchers working on miscommunication from two complementary perspectives. One group of technology-oriented researchers was made up of roboticists, Human-Robot Interaction (HRI) researchers and dialogue system experts. The second group involved experts from conversation analysis, cognitive science, and linguistics. Uniting both groups of researchers is the belief that communication failures between humans and machines need to be taken seriously and that a systematic analysis of such failures may open fruitful avenues in research beyond current practices to improve such systems, including both speech-centric and multimodal interfaces. This workshop represents a starting point for this endeavour. The aim of the workshop was threefold: Firstly, to establish an interdisciplinary network of researchers that share a common interest in investigating communicative failures with a particular view towards robotic speech interfaces; secondly, to gain a partial overview of the “failure landscape” as experienced by roboticists and HRI researchers; and thirdly, to determine the potential for creating a robotic benchmark scenario for testing future speech interfaces with respect to the identified failures. The present article summarizes both the “failure landscape” surveyed during the workshop as well as the outcomes of the attempt to define a benchmark scenario.

15 November 2019 in ACM Transactions on Human-Robot Interaction
Verified
Journal Article
Open access
PDF file
FFFrank Foerster
Frank Foerster
JSJoe Saunders
Joe Saunders
HLHagen Lehmann
Hagen Lehmann
CNChrystopher L. Nehaniv
Chrystopher L. Nehaniv
“No” is one of the first ten words used by children and embodies the first form of linguistic negation. Despite its early occurrence, the details of its acquisition remain largely unknown. The circumstance that “no” cannot be construed as a label for perceptible objects or events puts it outside the scope of most modern accounts of language acquisition. Moreover, most symbol grounding architectures will struggle to ground the word due to its non-referential character. The presented work extends symbol grounding to encompass affect and motivation. In a study involving the child-like robot iCub, we attempt to illuminate the acquisition process of negation words. The robot is deployed in speech-wise unconstrained interaction with participants acting as its language teachers. The results corroborate the hypothesis that affect or volition plays a pivotal role in the acquisition process. Negation words are prosodically salient within prohibitive utterances and negative intent interpretations such that they can be easily isolated from the teacher’s speech signal. These words subsequently may be grounded in negative affective states. However, observations of the nature of prohibition and the temporal relationships between its linguistic and extra-linguistic components raise questions over the suitability of Hebbian-type algorithms for certain types of language grounding.

19 July 2023
Verified
Conference Paper
Open access
FFFrank Foerster
Frank Foerster
MRMarta Romeo
Marta Romeo
PHPatrick Holthaus
Patrick Holthaus
BNBirthe Nesset
Birthe Nesset
MTMaria J. Galvez Trigo
Maria J. Galvez Trigo
JFJoel E. Fischer
Joel E. Fischer
In order to carry out human-robot collaborative tasks efficiently, robots have to be able to communicate with their human counterparts. In many applications, speech interfaces are deployed as a way to empower robots with the ability to communicate. Despite the progress made in speech recognition and (multi-modal) dialogue systems, such interfaces continue to be brittle in a number of ways and the experience of the failure of such interfaces is commonplace amongst roboticists. Surprisingly, a rigorous and complete analysis of communicative failures is still missing, and the technical literature is positively skewed towards the success and good performance of speech interfaces. In order to address this blind spot and investigate failures in conversations between humans and robots, an interdisciplinary effort is necessary. This workshop aims to raise awareness of said blind spot and provide a platform for discussing communicative troubles and failures in human-robot interactions and potentially related failures in non-robotic speech interfaces. We aim to bring together researchers studying communication in different fields, to start a scrupulous investigation into communicative failures, to begin working on a taxonomy of such failures, and enable a preliminary discussion on possible mitigating strategies. This workshop intends to be a venue where participants can freely discuss the failures they have encountered, to positively and constructively learn from them.

16 January 2021 in AI & SOCIETY
Verified
Journal Article
Open access
PDF file
FFFrank Foerster
Frank Foerster
Kaspar AlthoeferKaspar Althoefer
Kaspar Althoefer
The false attribution of autonomy and related concepts to artificial agents that lack the attributed levels of the respective characteristic is problematic in many ways. In this article, we contrast this view with a positive viewpoint that emphasizes the potential role of such false attributions in the context of robotic language acquisition. By adding emotional displays and congruent body behaviors to a child-like humanoid robot’s behavioral repertoire, we were able to bring naïve human tutors to engage in so called intent interpretations. In developmental psychology, intent interpretations can be hypothesized to play a central role in the acquisition of emotion, volition, and similar autonomy-related words. The aforementioned experiments originally targeted the acquisition of linguistic negation. However, participants produced other affect- and motivation-related words with high frequencies too and, as a consequence, these entered the robot’s active vocabulary. We will analyze participants’ non-negative emotional and volitional speech and contrast it with participants’ speech in a non-affective baseline scenario. Implications of these findings for robotic language acquisition in particular and artificial intelligence and robotics more generally will also be discussed.

24 November 2024
Verified
Conference Paper
Open access
CLCarlos Valter Baptista De Lima
Carlos Valter Baptista De Lima
JHJulian Hough
Julian Hough
FFFrank Foerster
Frank Foerster
PHPatrick Holthaus
Patrick Holthaus
YZYongjun Zheng
Yongjun Zheng
Achieving truly fluid interaction with robots with speech interfaces remains a hard problem. Despite technical advances in sensors, processors and actuators, the experience of Human-Robot Interaction (HRI) remains laboured and frustrating. Some of the barriers to this stem from a lack of a suitable development platform for HRI to improve the interaction, particularly for mobile manipulator robots. In this paper we briefly overview some existing systems and propose a high-fidelity Virtual Reality (VR) HRI simulation environment with Wizard-of-Oz (WoZ) cabability applicable to multiple robots including mobile manipulators and social robots.

10 March 2025 in Frontiers in Robotics and AI
Verified
Journal Article
Open access
PDF file
FFFrank Foerster
Frank Foerster
PHPatrick Holthaus
Patrick Holthaus
This research topic arose on the back of the WTF workshop series (Förster et al., 2022(Förster et al., , 2023a) ) that brought 2 together an interdisciplinary group of researchers ranging from roboticists and computational linguists to 3 conversation analysts and cognitive scientists to openly and frankly discuss failures of (robotic) speech 4 interfaces they experienced when deploying these in their studies. Some of the issues discussed in the 5 workshops are elaborated in the contributed articles below, more pointers can be found in the workshop 6 summary article by Förster et al. (2023b).This research topic contributes towards two main objectives: Firstly, we provide a platform for reporting 8 commonly occurring communicative failures in human-robot interaction (HRI). Secondly, this topic aims Galbraith (2024) investigate how virtual assistants deal with the interactionally highly relevant and 28 frequent 'huh?', an other-initiated, and likely universal repair marker (cf. Dingemanse et al., 2015). They further investigate what repair strategies these assistants utilise when encountering unintelligible speech, 30 and how native speakers judge these different repair strategies. In their study, two different virtual assistants, 31 Google Assistant and Apple's Siri, are compared across two different languages (English and Spanish).Galbraith finds that neither assistant actively produces 'huh?' but rather employs more specific repair 33 strategies when confronted with unintelligible speech. The assistants frequently have trouble dealing with a 34 'huh?' produced by human users, and some of the repair strategies employed by the two assistants were 35 rated negatively by human judges. While these insights were gained by interacting with virtual assistants, 36 we expect some of these to apply to SDS more generally (cf. Lopez et al., 2022).