Max Robotics — Global Service Robot Directory + US Certification

About

Chenrui Tie is a rising researcher at the intersection of 3D geometry, robotic manipulation, and embodied AI. Their work centers on two key challenges: enabling machines to understand and assemble 3D shapes, and equipping robots with the intelligence to manipulate arbitrary objects in the real world. Tie’s most cited paper, “Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly” (2023, 13 citations), introduces a novel approach to geometric part assembly—such as reconstructing a broken bowl from fragments—by exploiting symmetry properties in 3D space. This work addresses a fundamental gap between semantic part assembly and the more complex, unlabeled geometric assembly tasks. Building on this, Tie’s “ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis” (2024, 6 citations) proposes a large-scale model capable of handling diverse objects and robots, aiming to replicate the versatility of large language models in physical tasks. Most recently, “Manual2Skill” (2025, 3 citations) pushes further by enabling robots to read human manuals and learn furniture assembly skills using vision-language models. With a growing citation footprint and a clear trajectory toward general-purpose robotic intelligence, Tie is shaping how robots perceive, assemble, and interact with the physical world.