Max Robotics — Global Service Robot Directory + US Certification

About

Jad Abou-Chakra is a robotics researcher at the forefront of grounding large-scale machine learning models in the physical world. His work sits at the intersection of robot learning, computer vision, and language-guided manipulation, with a particular focus on enabling robots to operate in complex, unstructured environments. Abou-Chakra is a key contributor to the **Open X-Embodiment** collaboration, a landmark project that aggregated robotic data across 22 institutions to train the RT-X models. These works, cited over 220 times collectively, demonstrate that large, high-capacity models trained on diverse, cross-embodiment datasets can dramatically improve generalization and downstream task efficiency in robotics—mirroring the paradigm shifts seen in NLP and computer vision. His notable work **SayPlan** (2023, 30 citations) introduces a scalable method for grounding Large Language Models using 3D scene graphs, enabling robots to perform task planning across expansive, multi-floor environments. Additionally, his research on learning fabric manipulation from human videos and implicit object mapping with NeRFs tackles fundamental challenges in deformable object handling and real-world 3D perception. Abou-Chakra’s contributions are helping to build the data and algorithmic foundations for generalist, real-world robotic agents.