Task planning based on the interpretation of spatial structures

U ovom istraživanju razvijen je novi algoritam planiranja za transformaciju početnog neuređenog stanja objekata u uređeno konačno stanje. Zadatak algoritma planiranja je pronaći mogući niz djelovanja kojima se početno stanje okoline, kroz konačan broj diskretnih transformacija, može dovesti u zadano konačno stanje. Stanje okoline tumači se kroz položaj i orijentaciju objekata. Zadatak planiranja rješava se u dva koraka. Razvijena je konstruktivna heuristika pomoću koje se dobiva početni skup rješenja. Konstruktivna heuristika koristi mutacije za generiranje početne populacije. Genetski algoritam je razvijen za optimizaciju početnog skupa rješenja. Genetski algoritam karakteriziran je usporednom evolucijskom strategijom za pronalaženje rješenja, s ciljem prostorne pretvorbe neuređenog stanja objekata u uređeno, ograničen na dvodimenzionalnu interpretaciju radnog prostora. Verifikacija algoritma planiranja napravljena je u virtualnom okruženju.In this research, a new task planning algorithm is developed for building a desired object configuration from a given initial unordered object state. The task of the planning algorithm is to find a feasible set of actions, i.e. a finite number of discrete transformations, which can rearrange the objects into a desired ordered final state. The environment is interpreted through the position and orientation of the objects. The solution to the planning problem is proposed as a two-step method. First, a constructive heuristic generates an initial set of good solutions. The constructive heuristic uses only mutations for making an initial population of state transitions. A genetic algorithm is developed for optimizing the initial set of solutions. The genetic algorithm is characterized by a parallel evolutionary strategy, with the aim of spatial transformation of unordered object states into ordered object states. The algorithm can be used for solving the task planning problems represented in the two-dimensional space. Verification of the planning algorithm is done in a virtual environment