The 23rd IEEE International Symposium on Robot and Human Interactive Communication 2014
DOI: 10.1109/roman.2014.6926362
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Robots often have limited knowledge and need to continuously acquire new knowledge and skills in order to collaborate with its human partners. To address this issue, this paper describes an approach which allows human partners to teach a robot (i.e., a robotic arm) new high-level actions through natural language instructions. In particular, built upon the traditional planning framework, we propose a representation of high-level actions that only consists of the desired goal states rather than step-by-step oper… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
18
0

Year Published

2015
2015
2021
2021

Publication Types

Select...
7
2
1

Relationship

2
8

Authors

Journals

citations
Cited by 38 publications
(18 citation statements)
references
References 19 publications
0
18
0
Order By: Relevance
“…With the goal of encoding user preferences into reward functions guiding the behaviour of autonomous cars, they used an AL comparison approach, presenting informative pairs of synthesised driving trajectories to the users and asking for the preferred one. She et al [37] proposed a method to teach robots new high-level actions through natural language instructions, simplifying the addition of new skills. Hayes and Shah [19] leveraged the power of natural language to provide robots with ways of explaining their policies, simplifying their use with human collaborators.…”
Section: Related Workmentioning
confidence: 99%
“…With the goal of encoding user preferences into reward functions guiding the behaviour of autonomous cars, they used an AL comparison approach, presenting informative pairs of synthesised driving trajectories to the users and asking for the preferred one. She et al [37] proposed a method to teach robots new high-level actions through natural language instructions, simplifying the addition of new skills. Hayes and Shah [19] leveraged the power of natural language to provide robots with ways of explaining their policies, simplifying their use with human collaborators.…”
Section: Related Workmentioning
confidence: 99%
“…New functionality can be taught but the used language is rather technical. The approach by She et al allows the usage of everyday language to teach a robotic system new functionality [20]. For the transformation the approach uses semantic parsing.…”
Section: Related Workmentioning
confidence: 99%
“…To support action learning, previously we have developed a system where the robot can acquire the meaning of a new verb (e.g., stack) by following human's step-by-step language instructions (She et al, 2014a;She et al, 2014b). By performing the actions at each step, the robot is able to acquire the desired goal state associated with the new verb.…”
Section: Related Workmentioning
confidence: 99%