Max Robotics — Global Service Robot Directory + US Certification

About

Murad Dawood is a robotics researcher whose work sits at the intersection of reinforcement learning, control theory, and autonomous navigation. His key contributions span sparse-reward RL, safe multi-agent coordination, and state estimation for dynamic locomotion. In his 2023 paper on handling sparse rewards using model predictive control (13 citations), Dawood addresses a critical bottleneck in RL—the need for carefully engineered reward functions—by integrating MPC to guide learning in underdetermined environments. His 2025 work on safe multi-agent RL for cooperative navigation (8 citations) is the first to enable formation-based navigation without individual reference targets, a significant step for decentralized robot teams. Dawood has also advanced mapping for confined spaces with viewpoint push planning (8 citations) and introduced a Koopman operator-based centroidal state estimator for dynamic legged locomotion (4 citations), enabling linearized control of nonlinear systems. His 2025 paper on physically-consistent parameter identification for robots in contact (2 citations) addresses the practical challenge of obtaining accurate inertial data for robots like Spot. With a growing citation footprint and work spanning both theoretical and applied robotics, Dawood is establishing himself as a versatile researcher pushing the boundaries of autonomous, safe, and efficient robot behavior.