Max Robotics — Global Service Robot Directory + US Certification

About

Marco Piastra is a researcher whose work sits at the compelling intersection of robotics, machine learning, and autonomous systems, with a particular focus on intelligent control and motion planning for robotic manipulators. His most significant contributions center on applying Deep Reinforcement Learning (DRL) to solve real-world challenges in collision avoidance and path planning — problems that are critical to the safe deployment of robots in human-shared environments. Piastra's most impactful work, "Self-Configuring Robot Path Planning With Obstacle Avoidance via Deep Reinforcement Learning" (2020, 111 citations), introduced a hybrid control methodology enabling full-body collision avoidance in anthropomorphic manipulators, advancing classical motion planning by embedding DRL at its core. This built upon his earlier landmark contribution, "Deep Reinforcement Learning for Collision Avoidance of Robotic Manipulators" (2018, 92 citations), which pioneered real-time, machine-learning-driven safety mechanisms for human-robot coexistence. His work on self-configuring integral sliding mode control further demonstrates his commitment to adaptive, intelligent robot control architectures. With over 200 cumulative citations across his most prominent publications, Piastra has established himself as a meaningful contributor to the field of intelligent robotics, offering practical, learning-based solutions to some of the discipline's most pressing safety and autonomy challenges.