DM-MPPI: Datamodel for Efficient and Safe Model Path Integral Control

TL;DR

This paper introduces DM-MPPI, a novel influence prediction model that enhances the efficiency and safety of Model Predictive Path Integral control by enabling real-time sample influence estimation and adaptive constraint management.

Contribution

It extends the Datamodels framework to MPPI control, allowing direct influence prediction from sample features for real-time decision-making and improved safety.

Findings

Achieved up to 5x reduction in sample size without performance loss.

Enhanced constraint satisfaction through adaptive influence monitoring.

Demonstrated effectiveness in obstacle avoidance path-tracking tasks.

Abstract

We extend the Datamodels framework from supervised learning to Model Predictive Path Integral (MPPI) control. Whereas Datamodels estimate sample influence via regression on a fixed dataset, we instead learn to predict influence directly from sample cost features, enabling real-time estimation for newly generated samples without online regression. Our influence predictor is trained offline using influence coefficients computed via the Datamodel framework across diverse MPPI instances, and is then deployed online for efficient sample pruning and adaptive constraint handling. A single learned model simultaneously addresses efficiency and safety: low-influence samples are pruned to reduce computational cost, while monitoring the influence of constraint-violating samples enables adaptive penalty tuning. Experiments on path-tracking with obstacle avoidance demonstrate up to a $5\times$ reduction in the number of samples while maintaining control performance and improving constraint satisfaction.