Max Robotics — Global Service Robot Directory + US Certification

About

An Vuong is an emerging researcher at the intersection of robotics, computer vision, and embodied artificial intelligence, with a particular focus on enabling robots to perceive and interact with their environments more intelligently. His most recognized contribution, "Open-Vocabulary Affordance Detection in 3D Point Clouds" (2023), has garnered 27 citations and addresses a critical limitation in traditional robotics — the reliance on fixed, predefined affordance labels. By extending affordance detection to open-vocabulary settings using 3D point cloud data, Vuong's work significantly broadens the adaptability of intelligent robots in complex, real-world scenarios. His research further extends into language-driven robotic manipulation, as demonstrated in "Language-driven Grasp Detection with Mask-guided Attention" (2024), which integrates natural language understanding into grasp detection to overcome occlusion challenges. Additionally, his development of HabiCrowd (2024) advances embodied AI simulation by incorporating realistic human crowd dynamics, helping to bridge the gap between simulated training environments and real-world deployment. Collectively, Vuong's work reflects a coherent vision of building robots that are more contextually aware, linguistically guided, and practically deployable across dynamic human-centered environments.