Neural Distance-Guided Path Integral Control for Tractor-Trailer Navigation

2026-05-10

AI Summary

This study addresses the challenges of real-time obstacle avoidance and dynamically feasible control for articulated tractor-trailer systems operating in complex agricultural environments, where nonlinear dynamics and deformable geometry complicate navigation. To this end, the authors propose a novel framework that integrates a geometric neural encoder with Model Predictive Path Integral (MPPI) control. The encoder efficiently estimates the full-body geometric distance between the vehicle and obstacles directly from LiDAR point clouds and embeds this information into the MPPI cost function, enabling real-time, map-free safe navigation. This work presents the first integration of learning-based full-body distance perception with MPPI, facilitating trajectory optimization that respects the true articulated kinematics in dynamic, partially unknown settings. Simulations demonstrate that the approach generates safe, dynamically feasible, and responsive trajectories in cluttered scenarios, significantly enhancing the system’s environmental adaptability.

Abstract

Autonomous and safe navigation of tractor-trailer systems requires accurate, real-time collision avoidance and dynamically feasible control, particularly in cluttered and complex agricultural environments. This is challenging due to their articulated, deformable geometries and nonlinear dynamics. Traditional methods oversimplify vehicle geometry or rely on precomputed distance fields that assume a known map, limiting their applicability in dynamic, partially unknown environments. To address these limitations, we propose a geometric neural encoder that provides fast and accurate distance estimates between the full tractor-trailer body and raw LiDAR perception, enabling real-time, map-free geometric reasoning. These learned distances are integrated into a Model Predictive Path Integral (MPPI) controller, allowing the system to incorporate true articulated geometry directly into its cost evaluation and enabling more responsive navigation in challenging agricultural settings. Simulation results demonstrate that the proposed framework generates dynamically feasible and safe trajectories for navigating tractor-trailer systems in cluttered and complex environments.

Problem

• tractor-trailer navigation
• collision avoidance
• articulated geometry
• dynamic environments
• autonomous navigation

Innovation

• neural distance estimation
• tractor-trailer navigation
• Model Predictive Path Integral control
• LiDAR-based perception
• articulated vehicle geometry