| Breakthroughs in robotics have empower robots to execute increasingly intricate, human-centered tasks, driving significant research into motion planning and human-like arm movement. This growth makes manual literature reviews difficult to sustain and scale. To address this, the present work presents a framework for automated, large-scale bibliometric analysis of motion planners for robotic manipulators. The framework applies domain-specific Natural Language Processing to extract structured knowledge from full-text publications and to categorize studies across motion-planning dimensions. Rather than replacing expert reviews, it provides a reproducible, extensible means to systematically explore trends in human-like motion generation research and to accelerate discovery of influential methods, gaps, and emerging topics. The complete codebase and dataset are available to promote transparency and reuse. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.