Deep Normalizing Flows for State Estimation

TL;DR

This paper introduces a novel state estimation method using deep normalizing flows to better model complex, multi-modal distributions in robotic systems, outperforming traditional and deep learning baselines.

Contribution

The paper proposes an enhanced normalizing flow architecture for state estimation, providing more expressive belief representations in nonlinear, multi-modal scenarios.

Findings

Outperforms classical Gaussian filters in complex tasks

Achieves better accuracy than existing deep learning-based methods

Demonstrates effectiveness on two robotic state estimation benchmarks

Abstract

Safe and reliable state estimation techniques are a critical component of next-generation robotic systems. Agents in such systems must be able to reason about the intentions and trajectories of other agents for safe and efficient motion planning. However, classical state estimation techniques such as Gaussian filters often lack the expressive power to represent complex underlying distributions, especially if the system dynamics are highly nonlinear or if the interaction outcomes are multi-modal. In this work, we use normalizing flows to learn an expressive representation of the belief over an agent's true state. Furthermore, we improve upon existing architectures for normalizing flows by using more expressive deep neural network architectures to parameterize the flow. We evaluate our method on two robotic state estimation tasks and show that our approach outperforms both classical and modern deep learning-based state estimation baselines.