MBZUAI researchers have developed "Tactile Skills," a new embodied AI framework enabling robots to rapidly learn complex tactile tasks. The framework combines expert process knowledge with reusable tactile control and adaptation components, reducing reliance on extensive datasets. Tested on 28 industrial tasks, the robots achieved nearly 100% success, demonstrating adaptability to changing conditions. Why it matters: This breakthrough offers a practical and scalable approach to robotic automation, potentially transforming robots into adaptable assistants across diverse industries in the GCC.
MBZUAI Professor Sami Haddadin and his team developed a new framework called Tactile Skills to teach robots manual skills through touch and trial and error. This framework aims to address the gap in robots' ability to learn basic physical tasks compared to AI's advancements in language and image generation. The research, published in Nature Machine Intelligence, focuses on enabling robots to perform manipulation skills at industrial levels with low energy and compute demands. Why it matters: This research could lead to robots capable of performing household maintenance, industrial tasks, and even assisting in medical or rehabilitation settings, potentially solving labor shortages in various sectors in the region and beyond.
Sami Haddadin from the Technical University of Munich (TUM) discusses a shift in robotics towards machines that autonomously develop their own blueprints and controls. He highlights advancements driven by human-centered design, soft control, and model-based machine learning, enabling human-robot collaboration in manufacturing and healthcare. Haddadin also presents progress towards autonomous machine design and modular control architectures for complex manipulation tasks. Why it matters: This research has implications for advancing robotics and AI in the GCC region, especially in manufacturing and healthcare, by enabling safer and more efficient human-robot collaboration.
MBZUAI researchers have developed a "divide-and-conquer" technique to improve learning from demonstration in robotics. The approach breaks down complex dynamical systems into independently solvable subsystems, modeled as linear parameter-varying systems. This method aims to simplify computations while maintaining stability and accurately capturing joint interactions for robots in complex environments. Why it matters: The research addresses a key challenge in robotics, potentially enabling more efficient and safer robot learning from human demonstrations.
Michael Yu Wang, Chair Professor and Founding Dean of the School of Engineering at Great Bay University, argues for combining "good old fashioned engineering" (GOFE) with learning-based approaches like LLMs for robot skill acquisition, particularly in manipulation. He suggests a modular framework that integrates engineering principles with learning, drawing inspiration from human hand-eye coordination and tactile perception. Wang emphasizes the need to address engineering features of robot tactile sensors, such as spatial and temporal resolutions, to achieve human-like robot manipulation skills. Why it matters: This perspective highlights the importance of hybrid approaches combining traditional engineering with modern AI for advancing robotics, especially in complex manipulation tasks relevant to industries in the GCC region.