Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

A New Action Execution Module for the Learning Intelligent Distribution Agent (LIDA): The Sensory Motor System

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

This paper presents a cognitive model for an action execution process—the sensory motor system (SMS)—as a new module of the system-level cognitive model for “Learning Intelligent Distribution Agent” (LIDA). Action execution refers to a situation in which a software agent or robot transforms a selected goal-directed action into low-level executable actions and executes them in the real world. A sensorimotor system derived from the subsumption architecture has been implemented into the SMS; several cognitive neuroscience hypotheses have been incorporated as well, including the two visual systems. A computational SMS has been created inside a LIDA-based software agent in Webots to model the execution of a grip action; its simulated results have been verified against human performance. This computational verification by the comparison of model and human behaviors supports the SMS as a qualitatively reasonable cognitive model for action execution. Finally, the SMS has been compared with other alternative models of action execution; this supports the assertion that our new action execution module is applicable across a range of cognitive architectures.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. For historical reasons, LIDA stands for Learning Intelligent Distribution Agent.

  2. In this paper, we will only be concerned with the external environment, and not with LIDA’s internal environment.

  3. In the LIDA Model, the concept of ventral and dorsal streams for the transmission of visual information has been extended to multimodal transmission.

  4. Action learning is not yet implemented.

  5. In LIDA, the dorsal stream channel directly passes sensory data from the sensory memory to the action execution process.

  6. In this context, the term “action” refers to a component of a behavior. This differs from the general usage, such as in the phrase “action execution”. In this paper, we use “action” in the general sense, while “action of a behavior” refers to a particular component of that behavior.

  7. ‘An explicit desire to perform the action’ refers to a selected behavior; ‘a different mechanism’ is our SMS; and ‘the representation [that] loses its explicit character’ indicates executable motor commands.

  8. In comparison with the original design 19.Connell JH. A colony architecture for an artificial creature. DTIC Document, 1989., the cradle level, the back module, and the edge module were removed in the simulation because either their function is substituted for by the Webots simulated environment, or they are irrelevant to the hand and arm actuators.

  9. The Webots Supervisor "is a privileged type of Robot that can execute operations that can normally only be carried out by a human operator and not by a real robot” (www.cyberbotics.com). It is irrelevant to the machine learning concept of supervised learning.

  10. There is only very limited direct connectivity between perceptual and motor modules. Spatial information in particular is communicated directly.

  11. Although no central world state is one of the essences of the subsumption architecture, implicit understanding and expectation of the environment has been built into the architecture by its layered structure.

  12. There is the learning of implicit knowledge (the back-propagation network) at the bottom level. “In this learning setting, there is no need for external teachers providing desired input/output mappings. This (implicit) learning method may be cognitively justified” [28].

References

  1. Franklin S, Madl T, D’Mello S, Snaider J. LIDA: a systems-level architecture for cognition, emotion, and learning. IEEE Trans Auton Ment Dev. 2014;6(1):19–41.

    Article  Google Scholar 

  2. Franklin S, Graesser A. Is it an agent, or just a program?: a taxonomy for autonomous agents. Intelligent agents III agent theories, architectures, and languages. Springer: London; 1997. p. 21–35.

    Book  Google Scholar 

  3. Goodale MA, Milner AD. Separate visual pathways for perception and action. Trends Neurosci. 1992;15(1):20–5.

    Article  CAS  PubMed  Google Scholar 

  4. Milner D, Goodale MA. Two visual systems re-viewed. Neuropsychologia. 2008;46(3):774–85.

    Article  CAS  PubMed  Google Scholar 

  5. Goodale MA. Separate visual systems for perception and action: a framework for understanding cortical visual impairment. Dev Med Child Neurol. 2013;55(s4):9–12.

    Article  PubMed  Google Scholar 

  6. Goodale MA. How (and why) the visual control of action differs from visual perception. Proc R Soc B Biol Sci. 2014;281(1785):20140337.

    Article  Google Scholar 

  7. Milner A. Is visual processing in the dorsal stream accessible to consciousness? Proc R Soc B Biol Sci. 2012;279(1737):2289–98.

    Article  CAS  Google Scholar 

  8. Brooks RA. A robust layered control system for a mobile robot. IEEE J Robot Autom. 1986;2(1):14–23.

    Article  Google Scholar 

  9. Brooks RA. How to build complete creatures rather than isolated cognitive simulators. Architectures for intelligence: the twenty-second carnegie mellon symposium on cognition. 1991. p. 225–39.

  10. Maes P, Brooks RA. Learning to coordinate behaviors. In: Proceedings of the eighth national conference on artificial intelligence. Boston: Morgan Kaufmann; 1990. p. 796–802.

  11. Mahadevan S, Connell J. Automatic programming of behavior-based robots using reinforcement learning. Artif Intell. 1992;55(2):311–65.

    Article  Google Scholar 

  12. Wolpert DM, Diedrichsen J, Flanagan JR. Principles of sensorimotor learning. Nat Rev Neurosci. 2011;12(12):739–51.

    CAS  PubMed  Google Scholar 

  13. Weng JJ. The developmental approach to intelligent robots. AAAI spring symposium series, integrating robotic research: taking next leap. Stanford; 1998.

  14. Weng J. Developmental robotics: theory and experiments. Int J Humanoid Robot. 2004;1(02):199–236.

    Article  Google Scholar 

  15. Franklin S, Strain S, Snaider J, McCall R, Faghihi U. Global workspace theory, its LIDA model and the underlying neuroscience. Biol Inspir Cognit Archit. 2012;1:32–43.

    Google Scholar 

  16. Baars BJ. A cognitive theory of consciousness. New York: Cambridge University Press; 1988.

    Google Scholar 

  17. Baars BJ. The conscious access hypothesis: origins and recent evidence. Trends Cognit Sci. 2002;6(1):47–52.

    Article  Google Scholar 

  18. Baars BJ, Gage NM. Fundamentals of cognitive neuroscience: a beginner’s guide. London: Academic Press; 2013.

    Google Scholar 

  19. Connell JH. A colony architecture for an artificial creature. DTIC Document, 1989.

  20. Brooks RA. Elephants don’t play chess. Robot Auton Syst. 1990;6(1):3–15.

    Article  Google Scholar 

  21. Searle JR. Intentionality: an essay in the philosophy of mind. Cambridge: Cambridge University Press; 1983.

    Book  Google Scholar 

  22. Jeannerod M. Motor cognition: what actions tell the self. Oxford: Oxford University Press; 2006.

    Book  Google Scholar 

  23. De Vega M, Glenberg AM, Graesser AC. Symbols and embodiment: debates on meaning and cognition. Oxford: Oxford University Press; 2008.

    Book  Google Scholar 

  24. Simon HA. The sciences of the artificial. Cambridge: The MIT Press; 1969.

    Google Scholar 

  25. Cutsuridis V, Taylor JG. A cognitive control architecture for the perception—action cycle in robots and agents. Cognit Comput. 2013;5(3):383–95.

    Article  Google Scholar 

  26. Grafton ST. The cognitive neuroscience of prehension: recent developments. Exp Brain Res. 2010;204(4):475–91.

    Article  PubMed Central  PubMed  Google Scholar 

  27. Snaider J, McCall R, Franklin S. The LIDA framework as a general tool for AGI. Artificial general intelligence. Berlin: Springer; 2011. p. 133–42.

    Book  Google Scholar 

  28. Connell JH. A behavior-based arm controller. Robot Autom IEEE Trans. 1989;5(6):784–91.

    Article  Google Scholar 

  29. Jeannerod M. Intersegmental coordination during reaching at natural visual objects. Atten Perform IX. 1981;9:153–68.

    Google Scholar 

  30. James TW, Culham J, Humphrey GK, Milner AD, Goodale MA. Ventral occipital lesions impair object recognition but not object-directed grasping: an fMRI study. Brain. 2003;126(11):2463–75.

    Article  PubMed  Google Scholar 

  31. Milner D, Perrett D, Johnston R, Benson P, Jordan T, Heeley D, et al. Perception and action in ‘visual form agnosia’. Brain. 1991;114(1):405–28.

    Article  PubMed  Google Scholar 

  32. Farnè A, Pavani F, Meneghello F, Làdavas E. Left tactile extinction following visual stimulation of a rubber hand. Brain. 2000;123(11):2350–60.

    Article  PubMed  Google Scholar 

  33. Jakobson L, Archibald Y, Carey D, Goodale MA. A kinematic analysis of reaching and grasping movements in a patient recovering from optic ataxia. Neuropsychologia. 1991;29(8):803–9.

    Article  CAS  PubMed  Google Scholar 

  34. Jeannerod M, Decety J, Michel F. Impairment of grasping movements following a bilateral posterior parietal lesion. Neuropsychologia. 1994;32(4):369–80.

    Article  CAS  PubMed  Google Scholar 

  35. Byrne MD, Anderson JR. Serial modules in parallel: the psychological refractory period and perfect time-sharing. Psychol Rev. 2001;108(4):847–69.

    Article  CAS  PubMed  Google Scholar 

  36. Laird JE. Extending the Soar cognitive architecture. Artificial general intelligence. Memphis: IOS Press; 2008. p. 224–35.

  37. Laird JE, Congdon CB, Coulter KJ, Derbinsky N, Xu J. The soar user’s manual 9.4.0. 2014. http://web.eecs.umich.edu/~soar/downloads/Documentation/SoarManual.pdf. Accessed Dec 31.

  38. Sun R. The CLARION cognitive architecture: extending cognitive modeling to social simulation. In: Sun R, editor. Cognition and multi-agent interaction. New York: Cambridge University Press; 2006. p. 79–99.

    Google Scholar 

  39. Sun R. A tutorial on CLARION 5.0. 2014. http://www.cogsci.rpi.edu/~rsun/sun.tutorial.pdf. Accessed Dec 31.

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Institute for Intelligent Systems, University of Memphis, Memphis, TN, USA

    Daqi Dong & Stan Franklin

  2. FedEx Institute of Technology #403h, 365 Innovation Dr., Memphis, TN, 38152, USA

    Daqi Dong

  3. FedEx Institute of Technology #312h, 365 Innovation Dr., Memphis, TN, 38152, USA

    Stan Franklin

Authors
  1. Daqi Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stan Franklin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Daqi Dong.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dong, D., Franklin, S. A New Action Execution Module for the Learning Intelligent Distribution Agent (LIDA): The Sensory Motor System. Cogn Comput 7, 552–568 (2015). https://doi.org/10.1007/s12559-015-9322-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-015-9322-3

Keywords

Search

Navigation