Pedro Morais

Papers

Total Citations

H-Index

About

Pedro Morais is a leading researcher in legged robotics, specializing in the intersection of deep reinforcement learning (DRL) and agile locomotion. His work addresses the critical challenge of bridging the gap between low-level control and high-level planning for dynamic robots. Morais’s major contributions include pioneering iterative DRL frameworks that streamline the design of complex locomotion skills, as demonstrated in his highly cited 2019 work (63 citations) on the Cassie robot. This research tackles the practical difficulties of reward function tuning and policy development, making DRL more accessible for real-world robotic applications. He further advanced the field by integrating Monte-Carlo planning with robust blind-walking controllers, enabling robots to perform agile, high-level activities beyond simple gait execution (2018, 18 citations). By combining model-based planning with learning-based control, Morais has pushed the boundaries of what legged robots can achieve, moving them from stable walking toward truly autonomous, adaptive behavior. His work is foundational for students and engineers seeking to deploy intelligent locomotion in unstructured environments.