Mobile robot path planning by means of case-based reasoning and rapidly-exploring random trees

Abstract eng:
The aim of the robot path planning is searching for a path from a robot start configuration to a goal configuration without collisions with known obstacles minimizing weight of the path. We consider a nonholonomic robot moving in a two-dimensional continuous space with known polygonal obstacles. When planning a path by Case-Based Reasoning, the most similar cases (already used paths or their parts) are searched for to be subsequently adapted to the new problem. Rapidly-exploring Random Trees are used to find the missing parts of the constructed paths or new paths if similar cases are not found or adapted solutions are not good enough.

• Export as: BibTeX | MARC | MARCXML | DC | EndNote | NLM | RefWorks
• Add to your basket