NPC: Neural Predictive Control for Fuel-Efficient Autonomous Trucks

TL;DR

This paper introduces Neural Predictive Control (NPC), a data-driven approach for fuel-efficient autonomous trucking that learns vehicle dynamics without physical models, achieving better fuel savings in simulations and real-world tests.

Contribution

The paper presents a novel neural network-based predictive control method that does not rely on physical vehicle models, using attention mechanisms to optimize fuel efficiency.

Findings

NPC achieves 2.41% more fuel savings in simulation.

NPC achieves 3.45% more fuel savings in highway testing.

The method outperforms traditional model-based control approaches.

Abstract

Fuel efficiency is a crucial aspect of long-distance cargo transportation by oil-powered trucks that economize on costs and decrease carbon emissions. Current predictive control methods depend on an accurate model of vehicle dynamics and engine, including weight, drag coefficient, and the Brake-specific Fuel Consumption (BSFC) map of the engine. We propose a pure data-driven method, Neural Predictive Control (NPC), which does not use any physical model for the vehicle. After training with over 20,000 km of historical data, the novel proposed NVFormer implicitly models the relationship between vehicle dynamics, road slope, fuel consumption, and control commands using the attention mechanism. Based on the online sampled primitives from the past of the current freight trip and anchor-based future data synthesis, the NVFormer can infer optimal control command for reasonable fuel consumption. The physical model-free NPC outperforms the base PCC method with 2.41% and 3.45% more significant fuel saving in simulation and open-road highway testing, respectively.