Learning from Demonstration for Robotic Deburring and Polishing: A Systematic Mapping Study

Contact-rich manufacturing processes such as surface cleaning, deburring, and polishing require precise force regulation and complex trajectory tracking that are challenging to automate using conventional robot programming methods. Learning from Demonstration (LfD) offers a powerful alternative to transfer these expert skills from human operators to robotic systems. The objective of this study is to systematically map academic publications addressing LfD applications in robotic deburring and polishing between 2016 and 2026, classify the algorithmic structures, sensory modalities, and control configurations employed, and identify key industrial integration challenges. In accordance with the PRISMA 2020 guidelines, a systematic search was conducted across Scopus, Web of Science, IEEE Xplore, and Google Scholar databases. Out of 288 initially retrieved records, duplicate removal and a two-stage screening process (title/abstract followed by full-text review) resulted in a final corpus of 24 primary studies included for qualitative synthesis. The included studies were classified into five algorithmic clusters: Dynamic Movement Primitives (DMPs) and variants (37.5%), probabilistic and statistical models (33.3%), deep learning and generative AI architectures (16.7%), autonomous dynamical systems (8.3%), and direct impedance control (4.2%). Force/torque sensing remains the dominant modality (70.8%), though recent years document a trend toward multimodal perception and generative action policies (e.g., Diffusion Policies). The findings confirm that while LfD offers substantial cost-reduction and flexibility benefits for small and medium-sized enterprises (SMEs), technical barriers such as the sim-to-real transfer gap, high-frequency impact dynamics in deburring, and the autonomous identification of local non-polishing areas (LNP-areas) continue to limit widespread industrial deployment.