Jordi Ramos

Papers

Total Citations

H-Index

About

Jordi Ramos is a rising star in embodied AI, whose work bridges the critical gap between simulation and real-world robotic perception. His primary research focuses on audio-visual navigation, multimodal sensor fusion, and sim-to-real transfer—areas where he has made pioneering contributions. In his landmark 2024 paper, "Sim2Real Transfer for Audio-Visual Navigation with Frequency-Adaptive Acoustic Field Prediction," Ramos tackles one of robotics' most stubborn challenges: enabling robots trained in virtual environments to navigate effectively using sound in the physical world. He introduced a frequency-adaptive acoustic field prediction method that accounts for real-world sound propagation, achieving robust policy transfer without requiring expensive real-world retraining. Despite its recent publication, this work has already garnered 4 citations, signaling its immediate impact on the field. Ramos’s approach is notable for its elegance—rather than forcing simulations to match reality, he adapts the robot’s acoustic understanding to bridge the domain gap. His research promises to unlock more natural human-robot interaction, where machines can follow sounds to find people or objects in complex environments. For students and researchers, Ramos exemplifies how creative problem-solving in sim-to-real transfer can accelerate the deployment of intelligent, perceptive robots.