Max Robotics — Global Service Robot Directory + US Certification

About

Vincent Scesa is a robotics researcher whose work lies at the intersection of neural control, bipedal locomotion, and bio-inspired mechanical design. His primary contributions focus on developing real-time neural control strategies for biped robot balance, particularly through the implementation of Continuous-Time Recurrent Neural Networks (CTRNNs) and the Backpropagation Through Time (BPTT) algorithm. His most cited work, "Real time implementation of CTRNN and BPTT algorithm to learn on-line biped robot balance: Experiments on the standing posture" (2010, 16 citations), demonstrates a practical, experimental approach to achieving stable standing posture in bipedal robots—a foundational challenge in humanoid robotics. Scesa also contributed to the ROBIAN project, designing and testing a torso mechanism for the ROBIAN biped robot (2005, 5 citations), which serves as a testbed for studying human locomotion and developing active/passive prosthetic devices. His additional studies on dynamic BPTT(h) learning algorithms and recurrent neural network equilibrium control (2006) further explore the influence of time window width on learning performance. Through his experimental, hardware-in-the-loop approach, Scesa has advanced the practical application of neural networks for real-time robot control, bridging computational learning theory with physical robotic systems.