Max Robotics — Global Service Robot Directory + US Certification

About

Francisco Leiva is a robotics researcher whose work sits at the intersection of deep reinforcement learning, computer vision, and autonomous navigation for humanoid and service robots. His most influential contribution, "Visual Navigation for Biped Humanoid Robots Using Deep Reinforcement Learning" (101 citations), pioneered a mapless navigation system that uses only color images and Deep Deterministic Policy Gradients (DDPG) to guide bipedal locomotion—a significant step toward truly autonomous humanoid robots that can operate without pre-built maps. Leiva further advanced safe robot movement with his work on collision avoidance for indoor service robots using multimodal deep reinforcement learning. In a creative twist, he also applied convolutional neural networks to humanoid soccer robotics, demonstrating that robots can play effectively without relying on color information—a breakthrough for the Standard Platform League. His research consistently pushes the boundaries of how legged robots perceive and interact with dynamic environments, making him a notable figure in the growing field of learning-based robot control.