AERO-MPPI: Anchor-Guided Ensemble Trajectory Optimization for Agile Mapless Drone Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xin, Huang, Rui, Tang, Longbin, Zhao, Lin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917355847680000
author Chen, Xin
Huang, Rui
Tang, Longbin
Zhao, Lin
author_facet Chen, Xin
Huang, Rui
Tang, Longbin
Zhao, Lin
contents Agile mapless navigation in cluttered 3D environments poses significant challenges for autonomous drones. Conventional mapping-planning-control pipelines incur high computational cost and propagate estimation errors. We present AERO-MPPI, a fully GPU-accelerated framework that unifies perception and planning through an anchor-guided ensemble of Model Predictive Path Integral (MPPI) optimizers. Specifically, we design a multi-resolution LiDAR point-cloud representation that rapidly extracts spatially distributed "anchors" as look-ahead intermediate endpoints, from which we construct polynomial trajectory guides to explore distinct homotopy path classes. At each planning step, we run multiple MPPI instances in parallel and evaluate them with a two-stage multi-objective cost that balances collision avoidance and goal reaching. Implemented entirely with NVIDIA Warp GPU kernels, AERO-MPPI achieves real-time onboard operation and mitigates the local-minima failures of single-MPPI approaches. Extensive simulations in forests, verticals, and inclines demonstrate sustained reliable flight above 7 m/s, with success rates above 80% and smoother trajectories compared to state-of-the-art baselines. Real-world experiments on a LiDAR-equipped quadrotor with NVIDIA Jetson Orin NX 16G confirm that AERO-MPPI runs in real time onboard and consistently achieves safe, agile, and robust flight in complex cluttered environments. Code is available at https://github.com/XinChen-stars/AERO_MPPI.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17340
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AERO-MPPI: Anchor-Guided Ensemble Trajectory Optimization for Agile Mapless Drone Navigation
Chen, Xin
Huang, Rui
Tang, Longbin
Zhao, Lin
Robotics
Systems and Control
Agile mapless navigation in cluttered 3D environments poses significant challenges for autonomous drones. Conventional mapping-planning-control pipelines incur high computational cost and propagate estimation errors. We present AERO-MPPI, a fully GPU-accelerated framework that unifies perception and planning through an anchor-guided ensemble of Model Predictive Path Integral (MPPI) optimizers. Specifically, we design a multi-resolution LiDAR point-cloud representation that rapidly extracts spatially distributed "anchors" as look-ahead intermediate endpoints, from which we construct polynomial trajectory guides to explore distinct homotopy path classes. At each planning step, we run multiple MPPI instances in parallel and evaluate them with a two-stage multi-objective cost that balances collision avoidance and goal reaching. Implemented entirely with NVIDIA Warp GPU kernels, AERO-MPPI achieves real-time onboard operation and mitigates the local-minima failures of single-MPPI approaches. Extensive simulations in forests, verticals, and inclines demonstrate sustained reliable flight above 7 m/s, with success rates above 80% and smoother trajectories compared to state-of-the-art baselines. Real-world experiments on a LiDAR-equipped quadrotor with NVIDIA Jetson Orin NX 16G confirm that AERO-MPPI runs in real time onboard and consistently achieves safe, agile, and robust flight in complex cluttered environments. Code is available at https://github.com/XinChen-stars/AERO_MPPI.
title AERO-MPPI: Anchor-Guided Ensemble Trajectory Optimization for Agile Mapless Drone Navigation
topic Robotics
Systems and Control
url https://arxiv.org/abs/2509.17340