Max Robotics — Global Service Robot Directory + US Certification

About

Simone Calderara is a prominent researcher whose work sits at the intersection of computer vision, deep learning, and autonomous systems. His scholarship is particularly distinguished by foundational contributions to human trajectory prediction — a critical capability for self-driving vehicles, social robots, and intelligent surveillance systems. Calderara has consistently tackled the inherent complexity of human motion, which is multimodal, context-dependent, and socially influenced, developing increasingly sophisticated neural architectures to address these challenges. Among his most impactful contributions are DAG-Net, a Double Attentive Graph Neural Network for trajectory forecasting (58–71 citations across versions), and the Goal-driven Self-Attentive Recurrent Networks framework, which incorporates destination awareness into motion prediction (61 citations). His AC-VRNN model further advances multi-future trajectory generation using conditional variational recurrent networks (36 citations). Beyond pedestrian motion, Calderara has also made meaningful contributions to robotic perception, including a widely cited deep learning approach to vision-guided robotic grasping of unknown objects (63 citations). Collectively, his body of work reflects a sustained effort to equip autonomous agents with the perceptual and predictive intelligence needed to navigate human-centered environments safely and effectively, earning him growing recognition within the robotics and computer vision communities.