Riley Simmons-Edler

Papers

Total Citations

H-Index

About

Riley Simmons-Edler is a robotics researcher whose work bridges the critical gap between safe physical interaction and intelligent decision-making in autonomous systems. Their research centers on two key areas: collision avoidance through novel sensing paradigms and reinforcement learning for continuous control. In their highly cited work "AuraSense" (2021, 20 citations), Simmons-Edler introduced a groundbreaking approach to robot safety by enabling full-surface proximity detection, allowing robots to perceive obstacles across their entire body rather than just at discrete points—a fundamental advancement for operation in crowded human environments. Complementing this physical safety work, their influential paper "Q-Learning for Continuous Actions with Cross-Entropy Guided Policies" (2019, 15 citations) tackles the challenging problem of off-policy reinforcement learning in robotics, where data collection is expensive. By integrating cross-entropy methods with Q-learning, they developed a more efficient approach for robots to learn smooth, continuous actions without the instability that often plagues such methods. Together, these contributions demonstrate Simmons-Edler's commitment to making robots both safer and smarter—enabling them to navigate complex, dynamic spaces while learning more effectively from limited real-world experience.