Angel Martiez-Gonzalez

About

Angel Martínez-González has pioneered the intersection of depth sensing and deep learning for human-robot interaction (HRI). His most influential work, "Real-time Convolutional Networks for Depth-based Human Pose Estimation" (2018, 32 citations), introduced a novel framework that leverages the structural simplicity of depth images to achieve fast, reliable multi-person pose estimation. By demonstrating that depth data requires less computational overhead than traditional RGB imagery, Martínez-González enabled real-time performance critical for responsive HRI. His key contributions lie in bridging computer vision and robotics, showing that specialized CNN architectures can extract skeletal information from depth streams with minimal latency. This work has directly impacted the design of safer, more intuitive collaborative robots that can anticipate human motion. Beyond this landmark paper, his research continues to explore efficient neural network designs for embodied AI systems, with a focus on reducing computational cost while maintaining accuracy. Martínez-González’s approach has influenced subsequent work in gesture recognition and human tracking for industrial and service robotics, cementing his role as a key figure in making real-time human-aware robotics practically viable.

Research Focus

Key Achievements

Top Papers

1. 1
   Real-time Convolutional Networks for Depth-based Human Pose Estimation

   32 citations · 2018

Key Collaborators

Contact & Links