Rethinking Grounding

@inproceedings{Ziemke1997RethinkingG,
  title={Rethinking Grounding},
  author={Tom Ziemke},
  year={1997}
}
The grounding problem is, generally speaking, the problem of how to embed an artificial agent into its environment such that its behaviour, as well as the mechanisms, representations, etc. underlying it, can be intrinsic and meaningful to the agent itself, rather than dependent on an external designer or observer. This paper briefly reviews Searle’s and Harnad’s analyses of the grounding problem, and then evaluates cognitivist and enactive approaches to overcoming it. It is argued that… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.

FILTER CITATIONS BY YEAR

1997
2016

CITATION STATISTICS

  • 10 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-7 OF 7 REFERENCES

discuss in detail the relation between the work of Sherrington (1906), Loeb (1918) and von Uexküll (1928) and recent work in embodied AI and cognitive science. The key points for the argument at hand

  • Sharkey, Ziemke
  • Living
  • 1998
Highly Influential
7 Excerpts

Brooks 1991a; Beer 1995). Thus, the enactive/robotic approach to AI does seem to follow Searle’s ‘recommendation

  • e.g, Varela
  • 1991

If an agent’s behaviour requires grounding, then obviously the ‘behaviourgenerating patterns

  • e.g, Maturana, Varela
  • Brooks 1991b; Clark
  • 1991

on the other hand, emphasizes the relevance of action, embodiment and agent-environment mutuality. Thus, in the enactive framework, cognition is not considered an abstract agent-internal

  • Varela
  • 1991

Similar Papers

Loading similar papers…