Conditional Neural Relational Inference for Interacting Systems

06/21/2021
by   Joao A. Candido Ramos, et al.
8

In this work, we want to learn to model the dynamics of similar yet distinct groups of interacting objects. These groups follow some common physical laws that exhibit specificities that are captured through some vectorial description. We develop a model that allows us to do conditional generation from any such group given its vectorial description. Unlike previous work on learning dynamical systems that can only do trajectory completion and require a part of the trajectory dynamics to be provided as input in generation time, we do generation using only the conditioning vector with no access to generation time's trajectories. We evaluate our model in the setting of modeling human gait and, in particular pathological human gait.

READ FULL TEXT
research
04/29/2019

Frontal Plane Bipedal Zero Dynamics Control

In bipedal gait design literature, one of the common ways of generating ...
research
02/13/2018

Neural Relational Inference for Interacting Systems

Interacting systems are prevalent in nature, from dynamical systems in p...
research
12/14/2018

Nonparametric inference of interaction laws in systems of agents from trajectory data

Inferring the laws of interaction between particles and agents in comple...
research
07/21/2020

Maximum likelihood estimation of potential energy in interacting particle systems from single-trajectory data

This paper concerns the parameter estimation problem for the quadratic p...
research
08/28/2022

Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network

Dynamical systems with interacting agents are universal in nature, commo...
research
06/15/2018

Discovering User Groups for Natural Language Generation

We present a model which predicts how individual users of a dialog syste...

Please sign up or login with your details

Forgot password? Click here to reset