Carlos Mastalli received the M.Sc. degree in mechatronics engineering from the Simón Bolı́var University, Caracas, Venezuela, in 2013 and the Ph.D. degree in bio-engineering and robotics from the Istituto Italiano di Tecnologia, Genoa, Italy, in 2017.* He is currently an Assistant Professor at Heriot-Watt University, Edinburgh, U.K. He is the Head of the Robot Motor Intelligence (RoMI) Lab affiliated with the National Robotarium and Edinburgh Centre for Robotics. He is also appointed as Research Scientist at IHMC, USA. Previously, he conducted cutting-edge research in several world-leading labs: Istituto Italiano di Tecnologia (Italy), LAAS-CNRS (France), ETH Z ̈urich (Switzerland), and the University of Edinburgh (UK). Carlos completed my PhD on “Planning and Execution of Dynamic Whole-Body Locomotion on Challenging Terrain” in April 2017 in the Dynamic Legged System lab at Istituto Italiano di Tecnologia.
The central topic of Carlos’ research career is how to build general motor intelligence that enables athletic behaviours, dexterous manipulation and sensory-driven motor control. To build such capabilities, my research focuses on both top-down (principles, abstractions) and bottom-down (stimuli, data) approaches. Most of my previous work develops top-down approaches using the formalism of optimal control and numerical optimisation. Those approaches had enabled agile and complex manoeuvres in robots with legs and arms. My publications in robotics top-tier venues such as ICRA, RAL, AURO and TRO are high impact. More recently, I have also been working on deep learning techniques to warm start optimal control solvers (i.e., a memory of motion) and to train neural networks that combine optimisation layers (i.e., differentiate optimal control algorithms)