Situated Dialogue Processing for Human-Robot Interaction

Kruijff, Geert-Jan M.; Lison, Pierre; Benjamin, Trevor; Jacobsson, Henrik; Zender, Hendrik; Kruijff-Korbayová, Ivana; Hawes, Nick

doi:10.1007/978-3-642-11694-0_8

Cited by 33 publications

(26 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, while research into social robotics and human-robot interaction is still in its infancy, we have already moved way beyond unresponsive, minimally responsive or predictable automatons. Steady progress is being made in natural language interpretation and production, using a mixture of shallow and deep techniques to work towards robust linguistic interaction with robots (Kruijff et al, 2009). Hardware is continuously being improved, with a recent focus on bipedal robots, compliant actuation, haptic sensing, robotic facial expressions and the principled design of the robot's overall physical appearance to achieve a certain effect for specific demography.…”

Section: University Of Plymouth Ukmentioning

confidence: 99%

Time will tell – why it is too early to worry

Belpaeme

Morse

2010

View full text Add to dashboard Cite

Section: University Of Plymouth Ukmentioning

confidence: 99%

Time will tell – why it is too early to worry

Belpaeme

Morse

2010

View full text Add to dashboard Cite

“…This proves an essential feature [112,65] to enable perspective-aware grounding of natural language, as we will see in next sections.…”

Section: Situated Speech Actsmentioning

confidence: 99%

“…We do not claim however any significant contribution to the field of theoritical computational linguists (see [65] for a survey of formal approaches to natural language processing in the robotics field): our main contribution here is the grounding of concepts involved in the human discourse through the robot's own knowledge. Section 5.2 presents the overall grounding process and section 5.3 proposes an analysis of the processing of three prototypical sentences.…”

Section: Related Workmentioning

confidence: 99%

“…Kruijff et al provides in [65] an up-to-date survey of literature on situated humanrobot dialogue, focusing on formal representation systems, bi-directionality of the interaction and context building. They point as well that, compared to the cognitive psychology community, the "situated AI" community started only recently to take into account agents focus, perspective and temporal projection abilities.…”

Section: Related Workmentioning

confidence: 99%

“…Cross-modal knowledge fusion [46] is well studied, and the interaction with natural language processing [65,64] is a particular emphasise of the project.…”

Section: Cast Knowledge Modelmentioning

confidence: 99%

See 2 more Smart Citations

Grounding the Interaction: Knowledge Management for Interactive Robots

Lemaignan

2013

Künstl Intell

View full text Add to dashboard Cite

Affordance‐based indirect task communication for astronaut‐robot cooperation

Heikkila¹,

Halme²,

Schiele³

2012

Journal of Field Robotics

View full text Add to dashboard Cite

The problem with human–robot task communication is that robots cannot understand complex human speech, whereas humans cannot efficiently use the fixed task request utterances required by robots. However, future planetary exploration missions will require astronauts on extravehicular activities to communicate task requests to robot assistants by using speech‐ and gesture‐type user interfaces that can be easily embedded in their space suits. The solution proposed in this paper is indirect task communication based on the humanlike ability to utilize object–action relationships in task communication. A conventional task communication method, in which the astronaut needs to communicate all the task parameters explicitly, is compared with communication methods where affordances, i.e., action possibilities, are used to complete the task communication. This comparison is done with three user experiments: one performed with a fully autonomous centauroid robot in a geological exploration work context and two with a simulated robot in a lander assembly work context. The experiments indicate that affordance‐based indirect task communication methods can be used to decrease both the human workload and the task communication times in a planetary exploration type of work context, and that combined direct and indirect task communication methods seem to be preferable from a human point of view. © 2012 Wiley Periodicals, Inc.

show abstract

Situated Dialogue Processing for Human-Robot Interaction

Cited by 33 publications

References 54 publications

Time will tell – why it is too early to worry

Time will tell – why it is too early to worry

Grounding the Interaction: Knowledge Management for Interactive Robots

Affordance‐based indirect task communication for astronaut‐robot cooperation

Contact Info

Product

Resources

About