Max Robotics — Global Service Robot Directory + US Certification

About

Siddharth Singh is pioneering the intersection of machine learning and robotic manipulation, with a focus on enabling robots to learn complex, energy-efficient, and collaborative behaviors. His research centers on three key areas: kinematic skill generalization, hierarchical task learning, and multi-manipulator coordination. Singh’s most impactful work introduces optimized Dynamic Movement Primitives (DMPs) for energy-efficient motion planning, a method that allows robots to generalize learned skills to new, dynamic scenarios—a critical step toward adaptable automation. His 2025 paper on this topic has already garnered 4 citations, signaling its early influence. In parallel, Singh addresses the long-horizon complexity of robotic assembly by proposing a hierarchical learning framework that leverages Learning from Demonstration (LfD), breaking down intricate manufacturing tasks into manageable, learnable sub-skills. To tackle the challenges of collaborative robotics, he has developed a multi-level approach combining Reinforcement Learning with DMPs for safe, collision-free coordination among multiple manipulators. While early in his career, Singh’s work is notable for its practical orientation toward real-world manufacturing, offering scalable solutions that reduce energy consumption and enhance task efficiency. His contributions are laying the groundwork for the next generation of intelligent, collaborative robotic systems.