Max Robotics — Global Service Robot Directory + US Certification

About

Ayako Amma is a robotics researcher whose work lies at the intersection of computer vision, robotic manipulation, and embodied AI. Her research focuses on bridging the gap between simulation and reality, enabling robots to perceive and interact with objects in unstructured environments. Amma’s most cited work, “Sim2Real Instance-Level Style Transfer for 6D Pose Estimation” (15 citations), addresses the critical domain gap between synthetic training data and real-world deployment—a fundamental challenge in modern robotics. She has also made notable contributions to incremental multi-view object detection from moving cameras, allowing robots to build robust object representations over time. Her work on continual open set domain adaptation for home robots tackles the practical challenge of recognizing known objects while ignoring novel ones in domestic settings. Most recently, Amma introduced ZeroGrasp, a zero-shot shape reconstruction framework for robotic grasping that simultaneously models geometry and generates grasps from partial information. Her research on next viewpoint recommendation for accurate pose estimation further demonstrates her systematic approach to perception. Amma’s work is particularly relevant for students and researchers interested in sim-to-real transfer, object recognition, and autonomous manipulation in service robotics.