Elad Newman
Papers
1
Total Citations
42
H-Index
1
About
Elad Newman is a robotics researcher whose work centers on the intersection of reinforcement learning, impedance control, and dexterous manipulation. His most cited paper, "Reinforcement Learning of Impedance Policies for Peg-in-Hole Tasks: Role of Asymmetric Matrices" (2022, 42 citations), addresses a fundamental challenge in industrial automation: enabling robots to perform precise assembly tasks without exhaustive task-specific programming. By demonstrating how reinforcement learning can optimize asymmetric impedance matrices for peg-in-hole insertions, Newman's research bridges the gap between classical control theory and modern learning-based approaches. This work has direct implications for manufacturing, where robots must adapt to variable environments and tolerances. Beyond this flagship study, Newman's broader contributions explore how robots can learn compliant behaviors that mirror human dexterity—a critical step toward flexible automation. His findings have been cited by researchers advancing both theoretical frameworks in robot learning and practical implementations in assembly lines. For students and researchers in robotics, Newman's work exemplifies how combining model-based control with data-driven methods can solve longstanding industrial challenges, making robots more adaptable and reducing the engineering burden for new tasks.
Research Focus
Key Achievements
Top Papers
- 1