Multistep Belief Space Dynamics Learning For Risk-Aware Control

TL;DR

This paper introduces a learning framework for predicting distributional dynamics to enable risk-aware, real-time Model Predictive Control for autonomous vehicles in complex environments.

Contribution

It proposes a structured learning approach for distributional dynamics, validated through extensive real-world off-road driving experiments.

Findings

The structured model improves prediction accuracy over unstructured models.

The framework enables the vehicle to adapt speed based on environmental risk.

The system demonstrates consistent, intelligent off-road driving behavior.

Abstract

As autonomous vehicles move from a simplified research setting to practical use, there exists a large gap between the dynamic behavior of a human driving and an autonomous system. Risk-aware behavior needs to naturally develop in order to scale to the demands of the real world. A major issue for risk-aware planning and control has been predicting how dynamical uncertainty evolves through time and optimizing plans that account for this without being overly conservative. Here, we present a learning framework to predict distributional dynamics that can be optimized in real time for Model Predictive Control (MPC). We explore the importance of structure when learning distributional dynamics for use in MPC. A rigorous ablation study is conducted on a large dataset of real world off-road driving that shows the impact of deviations from our proposed structure. Furthermore, we deploy our learned model and planning stack on a full sized vehicle in challenging off-road conditions. Our planning architecture is able to naturally regulate the speed of the vehicle based on the environment and consistently demonstrates intelligent behavior over miles of diverse terrain.