Incremental learning of environment interactive structures from trajectories of individuals
This work addresses the challenge of environment modeling for robotics or surveillance by enabling incremental learning of object influences from agent trajectories, though it appears incremental in method.
The paper tackles the problem of estimating the influence of unknown static objects on mobile agents by analyzing trajectory deviations, using artificial neural networks to learn non-parametric velocity fields incrementally, and it can determine object properties like position, size, and repulsive or attractive influence.
This work proposes a novel method for estimating the influence that unknown static objects might have over mobile agents. Since the motion of agents can be affected by the presence of fixed objects, it is possible use the information about trajectories deviations to infer the presence of obstacles and estimate the forces involved in a scene. Artificial neural networks are used to estimate a non-parametric function related to the velocity field influencing moving agents. The proposed method is able to incrementally learn the velocity fields due to external static objects within the monitored environment. It determines whether an object has a repulsive or an attractive influence and provides an estimation of its position and size. As stationarity is assumed, i.e., time-invariance of force fields, learned observation models can be used as prior knowledge for estimating hierarchically the properties of new objects in a scene.