Ross Brown

Papers

Total Citations

H-Index

About

Ross Brown is a robotics researcher whose work tackles one of the field’s most persistent challenges: the reality gap between simulation and real-world robot performance. His core research areas include simulated robotic manipulation, sim-to-real transfer, and human-robot interaction. Brown’s major contributions center on developing methods to make simulated robotics more reliable and transferable to physical systems. His 2019 paper “Benchmarking Simulated Robotic Manipulation Through a Real World Dataset” (27 citations) established a foundational benchmark that provides a real-world ground truth dataset for evaluating simulated manipulation tasks. He further advanced the field with “Traversing the Reality Gap via Simulator Tuning” (9 citations), which demonstrated that optimizing physics engine parameters can narrow the gap between simulation and reality. His most innovative work, “Follow the Gradient: Crossing the Reality Gap using Differentiable Physics (RealityGrad)” (4 citations), introduces a novel iterative approach combining live robot rollouts with differentiable physics for efficient sim-to-real transfer. Beyond technical contributions, Brown explores user experience in “My Little Robot: User Preferences in Game Agent Customization” (13 citations), investigating how customization affects human-agent relationships. His work bridges fundamental robotics challenges with practical applications in manipulation and human-robot interaction.