SAIL on Jan. 22, 1999 
SAIL on Oct. 1, 1998
This line of research is to advance artificial intelligence using what we call the developmental approach. This new approach is motivated by human cognitive and behavioral development from infancy to adulthood. It requires a fundamentally different way of addressing the issue of machine intelligence. We have introduced a new kind of algorithm: the developmental algorithms.
For humans, the developmental algorithm starts to run at the conception time of each human individual. This algorithm is responsible for whatever can happen through the entire life span of that individual. For machines, the developmental algorithm starts to run at the ``birth'' time of the machine. It runs to enable the machine to develop its cognitive and behavioral skills through direct interactions with its environment using its sensors and effectors.
The concept of developmental algorithm does not mean just to make machines to growth from small to big and from simple to complex. It must enable the machine to learn new tasks and, as a special case, new aspects of each complex task without a need for reprogramming.
The basic nature of developmental learning plays a central role in enabling a human being to incrementally scale his or her level of intelligence from ground up. In order to scale up the machine's capability to understand what happens around it, the learning mechanism embedded in a developmental algorithm must perform systematic self-organization, according to what it sensed, what it did, action imposed by the human when necessary, the reward it received from the humans, and the context.
In contrast with traditional thoughts that artificial intelligence should be studied within a narrow scope otherwise the complexity is out of control, the developmental approach aims to provide a broad and unified developmental framework, each is applicable to a wide variety of cognitive capabilities (e.g., vision, speech, language, haptic understanding), behavioral capabilities (e.g., reasoning, planning, communication, decision making, task execution) and the fusion of these capabilities. By the very nature of automated development, a developmental algorithm does not require humans to manually model task-specific cognition or behavior.
Why do we pursue this developmental approach? Existing approaches require human designers to explicitly program according to the tasks that the machine is supposed to execute. However, AI tasks require capabilities mentioned above which have proved to be too muddy to program effectively. Although a developmental algorithm is by no means simple, the new developmental approach does not require human programmers to understand the domain of tasks nor to predict them. Therefore, this approach does not only drastically reduced the programming burden, but also enables machines to develop capabilities or skills that the programmer does not have or are too muddy to be adequately understood by the programmer.
A machine is called an agent if it can sense using it sensors and can act using its effectors. A living machine is an agent that runs a developmental algorithm. SAIL is the name of our first prototype of a living machine.
How long can a living machine live? When the hardware of a living machine is warn or broken, the developmental algorithm with its learned knowledge can be downloaded from the machine and uploaded to a new physical machine. Therefore, unlike a biological brain, a developmental algorithm can run as long as we humans like.
Patent pending: ``Developmental Learning Machine and Method.'' US Patent
Office serial number: 08/167,751.
This line of work is supported in part by NSF, DARPA, Siemens Corporate Research, and Zyvex.
Weng, Juyang
Leader
Associate Professor
2129 Engineering Building
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI 48824
(517) 353-4388
weng@cse.msu.edu
http://www.cse.msu.edu/~weng/
Hwang, Wey-Shiuan
Research Associate
3115 Engineering Building
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI 48824
(517) 432-9475
hwangwey@cse.msu.edu
http://www.cse.msu.edu/~hwangwey/
Zhang, Yilu
Graduate Research Assistant
3115 Engineering Building
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI 48824
(517) 432-9475
zhangyil@cse.msu.edu
http://www.cse.msu.edu/~zhangyil
Zeng, Shuqing
Graduate Research Assistant
3115 Engineering Building
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI 48824
(517) 432-9473
zengshuq@cse.msu.edu
http://www.cse.msu.edu/~zengshuq
Wang, Jingliang
Graduate Research Assistant
2318 Engineering Building
PhD student in Department Mechanical Engineering
Michigan State University
East Lansing, MI 48824
(517) 432-9473
wangjin1@egr.msu.edu
Ebrom, Matthew Peter
Undergraduate Research Assistant
3115 Engineering Building
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI 48824
(517) 432-9473
ebrommat@cse.msu.edu
Smith, Rebecca Jeanne
Undergraduate Research Assistant
3115 Engineering Building
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI 48824
(517) 432-9475
smithr46@pilot.msu.edu
Brown, Kevin
Undergraduate Research Assistant
3115 Engineering Building
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI 48824
(517) 432-9474
brownk17@cse.msu.edu
J. Weng, W.
S. Hwang, Y. Zhang and C. Evans, ``Developmental robots: Theorey, Method
and Experimental Results,'' in Proc. 2nd Int'l Symposium on Humanoid
Robots, Tokyo, Japan, pp. 57- 64, Oct. 8- 9, 1999. Download PDF
file. J. Weng, C.
Evans, W. S. Hwang, and Y. B. Lee, ``The Developmental Approach to Artificial
Intelligence: Concepts, Developmental Algorithms and Experimental Results''
in Proc. NSF Design & Manufacturing Grantees Conference, , Queen
Mary, Long Beach, CA, Jan 5-8, 1999. Also, Technical Report MSU-CPS-98-25,
July, 1998. Download
PDF
from the conference website. Download PostScript. J. Weng, Y.
B. Lee and C. H. Evans, ``The developmental approach to multimedia speech
learning,'' in Proc. IEEE Int'l Conf. on Acoustics, Speech, and Signal
Processing, Phoenix, Arizona, vol. 6, pp. 3093 - 3096, March 15 - 19,
1999. Download PDF file. J. Weng, ``The
Developmental Approach to Intelligent Robots,'' in Proc. 1998 AAAI Spring
Symposium Series, Integrating Robotic Research: Taking The Next Leap ,
Stanford University, March 23-25, 1998. Download PDF
file. J. Weng, ``The
Living Machine Initiative,'' Technical Report MSU-CPS-96-60, Department
of Computer Science, MSU, December 1996. Download PDF
file.