Score: 2

Neural NMPC through Signed Distance Field Encoding for Collision Avoidance

Published: November 26, 2025 | arXiv ID: 2511.21312v1

By: Martin Jacquet, Marvin Harms, Kostas Alexis

Potential Business Impact:

Drones fly safely in new places alone.

Business Areas:
Indoor Positioning Navigation and Mapping

This paper introduces a neural Nonlinear Model Predictive Control (NMPC) framework for mapless, collision-free navigation in unknown environments with Aerial Robots, using onboard range sensing. We leverage deep neural networks to encode a single range image, capturing all the available information about the environment, into a Signed Distance Function (SDF). The proposed neural architecture consists of two cascaded networks: a convolutional encoder that compresses the input image into a low-dimensional latent vector, and a Multi-Layer Perceptron that approximates the corresponding spatial SDF. This latter network parametrizes an explicit position constraint used for collision avoidance, which is embedded in a velocity-tracking NMPC that outputs thrust and attitude commands to the robot. First, a theoretical analysis of the contributed NMPC is conducted, verifying recursive feasibility and stability properties under fixed observations. Subsequently, we evaluate the open-loop performance of the learning-based components as well as the closed-loop performance of the controller in simulations and experiments. The simulation study includes an ablation study, comparisons with two state-of-the-art local navigation methods, and an assessment of the resilience to drifting odometry. The real-world experiments are conducted in forest environments, demonstrating that the neural NMPC effectively performs collision avoidance in cluttered settings against an adversarial reference velocity input and drifting position estimates.

Country of Origin
🇳🇴 Norway

Repos / Data Links

Page Count
24 pages

Category
Computer Science:
Robotics