Max Robotics — Global Service Robot Directory + US Certification

About

Maryam Bandari is a robotics researcher whose work sits at the intersection of machine learning, manipulation, and motion planning. Her primary research areas include imitation learning for bimanual manipulation, multi-task learning for robotic systems, and the perception and manipulation of deformable objects. Bandari’s most cited paper, "A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies" (2022, 18 citations), introduces a framework that combines admittance control with machine learning to teach robots complex, contact-rich tasks from human demonstrations. This work addresses a critical challenge in robotics: enabling robots to perform bimanual tasks that require both compliance and precision. Her paper "Multi-Task Learning with Sequence-Conditioned Transporter Networks" (2022, 13 citations) advances the field of compositional manipulation by enabling robots to solve multiple tasks through a single, scalable learning approach. Bandari has also made notable contributions to deformable object manipulation, with work on routing and spatial representation of one-dimensional objects like cables and ropes (2022, 9 citations), as well as efficient motion planning through neural collision clearance estimators (2019, 9 citations; 2021, 8 citations). Her research has significant implications for industrial assembly, surgical robotics, and construction, where the ability to handle both rigid and deformable objects is essential. With a growing citation record and a focus on practical, scalable solutions, Bandari is establishing herself as a rising figure in modern robotics.