Max Robotics — Global Service Robot Directory + US Certification

About

Tianlei Jin is a robotics researcher whose work bridges computer vision, knowledge representation, and autonomous manipulation. His primary research areas include gaze-following for human-robot interaction, category-level 6D object pose estimation, whole-body motion planning, and knowledge-guided task planning for service robots. Jin’s most cited work, “Depth-aware gaze-following via auxiliary networks for robotics” (32 citations), introduces a method that leverages depth and orientation cues without requiring additional datasets, significantly improving how robots interpret human attention. In “KGNet: Knowledge-Guided Networks for Category-Level 6D Object Pose and Size Estimation” (15 citations), he addresses the critical limitation of CAD-model dependency in pose estimation, enabling robots to grasp novel objects. His 2024 paper on whole-body inverse kinematics and operation-oriented motion planning tackles the complex, high-degree-of-freedom challenge of mobile manipulation. Jin has also advanced tour-guide robotics through frameworks for task understanding and multi-person tracking, including the TGRMPT dataset. His recent work on referring expression comprehension in semi-structured human-robot interaction (2025) continues to push boundaries in natural language-guided robotics. With a growing citation record and contributions spanning perception, planning, and interaction, Jin is establishing himself as a versatile innovator in intelligent robotic systems.