Professional Documents
Culture Documents
482
0DQXDOFRQWURO 9LGHRFDSWXUH IV. C ONCLUSION
FRPSRQHQW LQ3&
In this paper, we present a scenario-based method for
safety certification of intelligent systems. With the method,
&RPPXQLFDWLRQ VRIWZDUHLQ the quantitative trustability of the software with AI modules
,PDJHSURFHVV 7&3,3573LQ DWPOV
$50 could be evaluated before invoked. For the method, we
should clarify two points:
3DWWHUQ 1) Enumerate all the elements influence the accuracy of
UHFRJQLWLRQ &RPPXQLFDWLRQ
56LQ$50 AI.
2) quantify the influences.
Figure 2. The architecture of the distributed software system. We should establish a scenario architecture to complete the
two task. However, in many applications, to finish the two
task many need AI algorithms. Then, it become a recursive
problem. We should avoid the conditions.
This paper is only an exploration on the topic, we’ll give
deep research and timely report in the future.
ACKNOWLEDGMENT
The tiny robot used in the case study is open
source and the source code is available by email now
(gqli@buaa.edu.cn). A website for the robot will be set up in
the recent future for downloading source code and providing
Figure 3. One of the characters the intelligent system should be recognized. related documents.
R EFERENCES
[1] Stanford Univesity autonomous helicopter. The goal of this
project is to push the state-of-the-art in autonomous helicopter
B. Determine the AI Component reliability with Scenario
flight: extreme aerobatics under computer control. Available at
http://heli.stanford.edu/.
Let’s consider a specific mission of the tiny robot. Figure
3 is a Chinese character means ”Stop”. The tiny robot [2] R. Varadaraju, ”A Survey of Introducing Ar-
tificial Intelligence Into the Safety Critical
capture 5 pieces of pictures every second. Then, do image System Software Design Process. Available” at:
process on the pictures. If a rectangle is recognized, then http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.114.8602
it will do character recognition. There are many Chinese
characters have been learned by the program. If the picture [3] A. Mili, G. Jiang, B. Cukic, Y. Liu and R. Ben Ayed, ”Towards
is recognized, corresponding command will be send to the the Verification and Validation of Online Learning Systems:
General Framework and Applications”. In Proceedings of
mechanical components ultimately. Hawaii International Conference on System Sciences. 2004.
It is obviously that the recognition accuracy is influenced
by the environment. For example, the light intensity, at [4] Z Kurd and T P Kelly, ”Using Safety Critical Artificial Neural
Networks in Gas Turbine Aero-Engine Control”. In Proceed-
daytime the recognition is about 96.7% and at twilight, ings of the 24 th International Conference on Computer Safety,
the accuracy is lower. Visibility is another scenario features Reliability and Security (SAFECOMP’05), September 2005
influence the recognition accuracy. (Springer Verlag Lecture Notes in Computer Science LNCS).
We add a light intensity sensor and a software component [5] S. M. Yacoub, B. Cukic and H. H. Ammar, ”Scenario-Based
to calculate the visibility of the environment to the tiny robot. Reliability Analysis of Component-Based Software”. In pro-
Then the recognition accuracy of the AI component could ceedings of the 10th International Symposium on Software Re-
be predictable. Adding the information to the scenario-based liability Engineering table of contents. EEE Computer Society
reliability analysis method for component-based software. Washington, DC, USA. 1999.
The quantitative reliability of the distributed software with [6] Cross-validation (statistics). From Wikipedia, the free encyclo-
AI modules could be evaluated before invoked, if the reli- pedia. http://en.wikipedia.org/wiki/Cross-validation
ability is satisfied, then the program will be performed for
safety-critical systems, otherwise it will be terminated to ask [7] Weidenhaupt, K., K. Pohl, M. Jarke, and P. Haumer, ”Scenarios
human assistance or postpone the missions. Additional, we in System Development: Current Practice”, IEEE Software,
March/April 1998, pp34-45.
should validate that the scenarios are completeness and cor-
rectness for the AI algorithm. That is feasible. Completeness,
correctness and etc. are jargons of safety engineers.
483