Ahmad Babaeian Jelodar

Papers

Total Citations

H-Index

About

Ahmad Babaeian Jelodar is a researcher at the forefront of robotic perception and computer vision, with a specialized focus on enabling machines to understand dynamic environments. His key research area centers on the novel problem of **object state recognition**, particularly within cooking-related contexts—a critical capability for kitchen robots that must interpret not just *what* an object is, but *how* it is being transformed (e.g., chopped, boiling, or raw). His most influential work, "Identifying Object States in Cooking-Related Images" (2018, 47 citations), is a pioneering contribution that formally introduced this challenge to the field, arguing that state identification is as vital as object detection for task planning. Jelodar further advanced this line of inquiry by leveraging deep learning architectures, such as Inception networks, to classify cooking states from images (2019, 22 citations). A hallmark of his approach is the integration of language knowledge to jointly recognize objects and their states, demonstrating that these two tasks are mutually reinforcing (2019, 13 citations). By bridging the gap between static object recognition and dynamic state understanding, Jelodar’s work lays essential groundwork for more intelligent, context-aware robotic assistants in unstructured environments.