Understanding Human Behavior

In this article, we introduce another aspect of our visual system. During the first Three Cup Monte Test for visual perception, we demonstrated the software capabilities to track objects and understand their movements and interaction in the outside world. This new demonstration will take our system to the next level: understanding human posture and motion. To this end, we show our system tracking a human skeleton through yoga poses in real-time based on physics principles. Our ambition is to make a robot understand human interactions within their environment to adapt and make their own decisions accordingly. This and our first demo let us test our system in different environments. The two demonstrations highlight our goal to create a generic system. This system should allow us to solve issues from a wide range of domains and facilitate specific developments for new problems. Part of our implementation will be published in 2021.