Incremental learning of environment interactive structures from trajectories of individuals

TL;DR

This paper introduces an incremental neural network-based method to detect and estimate the influence of static objects on mobile agents by analyzing trajectory deviations, enabling dynamic environment understanding.

Contribution

It presents a novel incremental learning approach for estimating static object influences from trajectory data using neural networks, including object influence type, position, and size.

Findings

Successfully estimates influence of static objects on agent trajectories.

Differentiates between attractive and repulsive object influences.

Learns environment static features incrementally over time.

Abstract

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.