Max Robotics — Global Service Robot Directory + US Certification

About

Jiageng Mao is a leading researcher at the intersection of 3D computer vision and robotic manipulation. His work primarily focuses on point cloud processing and generalizable robot learning, addressing fundamental challenges in how machines perceive and interact with the physical world. Mao’s most impactful contribution is the GRNet (Gridding Residual Network), introduced in 2020, which revolutionized dense point cloud completion. By replacing traditional MLP-based methods with a novel gridding and residual learning framework, GRNet preserves fine structural details from incomplete 3D scans—a critical advancement for autonomous driving and robotics. This work has garnered over 400 citations, cementing its status as a foundational method in the field. More recently, Mao has pushed the boundaries of scalable robot learning. His RoboVerse platform (2025) provides a unified benchmark and dataset for generalizable robot learning, while RAM (Retrieval-Based Affordance Transfer, 2024) introduces a zero-shot manipulation framework that generalizes across diverse objects, environments, and robot embodiments—eliminating the need for expensive in-domain demonstrations. Through these innovations, Mao is bridging the gap between perception and action, enabling robots to operate more flexibly in unstructured real-world settings.