Planning The Activity Of Robot With Artificial Intelligence

The paper dea ls w i t h a number of problems invo lved In p l a n n i n g a r o b o t ' s a c t i v i t y . A f o r m a l i z e d statement o f the p lann ing problem Is proposed and the t h e o r e t i c a l p r i n c i p l e s o f des ign and r e quirements to s t r u c t u r e o f the problem environment models and p l a n n i n g a l g o r i t h m s are d i scussed . A problem e n v i r o n ment model is conoelved as a set of int e r r e l a t e d data on the r e a l wor ld o f a r o b o t ' s f u n c t i o n i n g t h a t are necessary and s u f f i c i e n t f o r the s o l u t i o n o f a l l problems be long ing to a c e r t a i n c l a s s . A l go r i t hm is understood as a gene ra l i sed procedure de f i ned on a problem e n v i r o n ment model . Let us cons ider the f u n c t i o n i n g o f a c e r t a i n c l ass o f a r t i f i c i a l systems per fo rm ing a c t i o n s in a th ree -d imens iona l space. We s h a l l i n t r oduce the n o t i o n of the work ing space of a system, conce iv ing i t a s the space which i s p h y s i c a l l y access ib le to the system f o r pe r fo rm ing the a c t i o n s i t commits. Then by robo ts we s h a l l understand a c l a s s of f u n c t i o n a l l y s i m i l a r automata having a memory and in tended f o r execu t ing d i r e c t e d changes of the p r o p e r t i e s o f the components o f environment or r e l a t i o n s between these w i t h i n t h e i r work ing spaoe by means of man ipu la t i ons w i t h t o o l s and ( o r ) o b j e c t s . We presume the ex is tence of p o t e n t i a l f e a s i b i l i t y o f man ipu la t i ng accord ing t o any s p a c i a l law. The s imp les t r o b o t s are devices f u n c t i o n i n g on the bas i s o f a r i g i d p r o gram. Programs are supp l i ed to the robo t to be subsequent ly implemented in the form o f c e r t a i n i n f l u e n c e s on the e n v i ronment in a sequence which is in advance d e f i n e d by man ( i n the genera l case by a metasystem, i . e . system having a h ighe r l e v e l o f c o n t r o l a s compared w i t h the r o b o t ) . Moreover in some cases the cho ice of a c t i o n s of the robo t may be a d d i t i o n a l l y c o n t r o l l e d by changes o f i t s physi c a l s t a t e and resource c a p a c i t y . The f u r t h e r s o p h i s t i c a t i o n o f the robo ts a c companied by an inc rease of t h e i r a u t o nomy necess i t a tes i n c o r p o r a t i n g i n t h e i r c o n t r o l systems such mechanisms as a f foxd d u r i n g the cho ice o f a c t i o n a u t o m a t i c a l l y t o take account o f s i t u a t i o n s a r i s i n g in the r o b o t ' s work ing space (and in more developed systems a l s o s i t u a t i o n s embrac i n g the e n t i r e problem environment o f the robo t i s a p r e t r a i n e d system c l a s s i f y i n g s i t u a t i o n s a r i s i n g i n the e n v i ronment and choosing the a p r i o r i s t a t e d a c t i o n sequences t h a t are adequate to these s i t u a t i o n s . However, in complex e n v i ronments i n v o l v i n g a g rea t number of components which a f f e c t the r o b o t ' s a c t i v i t y , a n a p r i o r i c l a s s i f i c a t i o n o f s i t u a t i o n s may prove p r a c t i c a l l y imposs i b l e . In t h i s case the robot must be ab le to form independent ly the sequenoe of a c t i o n s t h a t would be adequate to any s i t u a t i o n a r i s i n g in the problem e n v i r o n ment, i . e . i t must be able to so lve the p l ann ing prob lem. The c o n t r o l system of the robo t must in t h i s case be p o t e n t i a l l y prepared f o r execu t ing a g rea t set o f a c t i o n s i n p e r c e p t i o n c o n t r o l o f movement of execu t i ve o rgans , d e c i s i o n making and d ia logue w i t h the metssystam. In pos ing tasks f o r the robo t and c o r r e c t i n g i t s a c t i v i t y b y way o f d i a l o -