Max Robotics — Global Service Robot Directory + US Certification

About

Jinghua Li is a leading researcher in computer vision and robotics, with a focused expertise in visual affordance recognition—a critical area for enabling intelligent systems to understand how objects can be used. Her work bridges the gap between perception and action, advancing deep learning methods that allow robots and AI to interpret object functions from visual data. Li’s major contributions include pioneering comprehensive surveys that unify the rapidly evolving field of deep learning-based affordance recognition, as demonstrated by her highly cited 2023 survey paper (17 citations). She has also developed innovative detection frameworks, such as ADOSMNet, which leverages object shape masks to improve affordance detection accuracy, and OASNet, a novel network that integrates joint visual features with relational semantic embeddings to recognize object affordance states—determining not just what an object can do, but whether it is currently being used. This work addresses a crucial gap in traditional affordance learning, with direct applications in robotic manipulation and human-computer interaction. With over 28 citations across her key publications, Li’s research continues to shape how machines perceive and interact with the physical world.