Anticipating human motion in crowded environments is essential for developing autonomous systems able to safely navigate public spaces or interact with humans. Navigation of such scenarios by self-driving cars or robots requires mimicking human perception and extracting social conventions in order to autonomously move in urban areas. Advanced video surveillance systems also require forecasting human positions for many tasks, e.g., behavior anomaly detection, space optimization and support to human operators. Intelligent transportation systems need anticipation capabilities and social-awareness for efficient scene navigation.
In the recent years, the growing interest of several scientific communities on human motion prediction has witnessed the need for standard benchmarks and metrics. To this end, the proposed workshop aims to foster networking among researchers dealing with trajectory forecasting task to lay the foundations for future research, powering discussions on applications, data and performances. The workshop also aims to give space to discuss open questions with researchers in computer vision, robotics and cognitive neuroscience areas to conceive autonomous systems able to proactively act in complex contexts involving humans and moving objects in a safely manner.

• Motion trajectory prediction in urban scenes

• Action and activity anticipation

• Crowd motion analysis

• Human dynamics modelling

• Visual scene analysis

• Human-robot interactions

• Path planning and optimization

• Anomaly detection

• Data fusion techniques

• Human perception

• Social-awareness analysis