Carl Gaebert

Chemnitz University of Technology, Human Computer Interaction (Switzerland)

Papers

Total Citations

H-Index

About

Carl Gaebert is a robotics researcher focused on advancing human-robot collaboration through intelligent motion planning and control. His primary research areas include sampling-based motion planning, inverse kinematics for humanoid robots, and legible robot motion generation. Gaebert’s most cited work, “Learning-based Adaptive Sampling for Manipulator Motion Planning” (2022, 9 citations), addresses a critical bottleneck in robotics: generating optimized motions quickly enough for fluent human-robot cooperation in shared workspaces. By integrating learning-based methods with traditional sampling-based planners, his approach improves initial solution quality without sacrificing convergence guarantees. In “Effects of Human-Like Characteristics in Sampling-Based Motion Planning on the Legibility of Robot Arm Motions” (2025, 2 citations), Gaebert explores how making robot motions more predictable and human-like can dramatically improve collaboration quality. His work “Generating Dual-Arm Inverse Kinematics Solutions using Latent Variable Models” (2024, 2 citations) tackles the complex challenge of producing self-collision-free motions for humanoid robots performing bimanual tasks. Together, Gaebert’s contributions bridge the gap between theoretical planning algorithms and practical, human-aware robot behavior, making him a rising voice in the field of collaborative robotics.