Max Robotics — Global Service Robot Directory + US Certification

About

Danilo Erricolo is a versatile researcher whose work spans autonomous robotics, uncertainty quantification, wireless communications, and microelectromechanical systems (MEMS). He has made significant contributions to the development of uncertainty-aware frameworks for edge robotics, addressing a critical gap in deploying AI systems on resource-constrained platforms such as insect-scale drones and surgical robots. His 2023 paper on lightweight, conformalized visual odometry (13 citations) pioneered the application of conformal prediction to autonomous navigation, providing reliable uncertainty estimates without sacrificing computational efficiency. Building on this, his 2024 work on multimodal 3D object detection (9 citations) introduced mutual information-calibrated conformal feature fusion, advancing robust perception in complex environments. Erricolo has also explored the promising frontier of Reconfigurable Intelligent Surfaces for industrial wireless communications, examining challenges and opportunities in optimizing signal propagation environments. His earlier work on heterogeneous MEMS microrobot control demonstrates a longstanding interest in precision robotics at the microscale. Most recently, he has extended his uncertainty-aware philosophy into deep reinforcement learning, combining calibrated quantile regression with evidential learning for safety-critical applications. Across these diverse domains, Erricolo's research consistently prioritizes reliability, safety, and real-world deployability.