Modeling continuous-time stochastic processes using N-Curve mixtures

08/12/2019
by   Ronny Hug, et al.
3

Representations of sequential data are commonly based on the assumption that observed sequences are realizations of an unknown underlying stochastic process, where the learning problem includes determination of the model parameters. In this context the model must be able to capture the multi-modal nature of the data, without blurring between modes. This property is essential for applications like trajectory prediction or human motion modeling. Towards this end, a neural network model for continuous-time stochastic processes usable for sequence prediction is proposed. The model is based on Mixture Density Networks using Bézier curves with Gaussian random variables as control points (abbrev.: N-Curves). Key advantages of the model include the ability of generating smooth multi-mode predictions in a single inference step which reduces the need for Monte Carlo simulation, as required in many multi-step prediction models, based on state-of-the-art neural networks. Essential properties of the proposed approach are illustrated by several toy examples and the task of multi-step sequence prediction. Further, the model performance is evaluated on two real world use-cases, i.e. human trajectory prediction and human motion modeling, outperforming different state-of-the-art models.

READ FULL TEXT

page 16

page 19

page 21

page 22

research
05/03/2022

Bézier Curve Gaussian Processes

Probabilistic models for sequential data are the basis for a variety of ...
research
07/11/2019

Kernel Trajectory Maps for Multi-Modal Probabilistic Motion Prediction

Understanding the dynamics of an environment, such as the movement of hu...
research
05/17/2020

AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction

Anticipating human motion in crowded scenarios is essential for developi...
research
02/01/2023

MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs

Enabling resilient autonomous motion planning requires robust prediction...
research
09/20/2023

Generalised Hyperbolic State-space Models for Inference in Dynamic Systems

In this work we study linear vector stochastic differential equation (SD...
research
10/08/2021

Temporal Convolutions for Multi-Step Quadrotor Motion Prediction

Model-based control methods for robotic systems such as quadrotors, auto...
research
02/01/2019

Limit theorems for cloning algorithms

Large deviations for additive path functionals of stochastic processes h...

Please sign up or login with your details

Forgot password? Click here to reset