SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Low, JunEn, Adang, Maximilian, Yu, Javier, Nagami, Keiko, Schwager, Mac
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910887809384448
author Low, JunEn
Adang, Maximilian
Yu, Javier
Nagami, Keiko
Schwager, Mac
author_facet Low, JunEn
Adang, Maximilian
Yu, Javier
Nagami, Keiko
Schwager, Mac
contents We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only onboard perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k image/state-action pairs from an expert MPC with privileged state and dynamics information, randomized over dynamics parameters and spatial disturbances. We then distill this expert MPC into an end-to-end visuomotor policy with a lightweight neural architecture, called SV-Net. SV-Net processes color image, optical flow and IMU data streams into low-level thrust and body rate commands at 20 Hz onboard a drone. Crucially, SV-Net includes a learned module for low-level control that adapts at runtime to variations in drone dynamics. In a campaign of 105 hardware experiments, we show SOUS VIDE policies to be robust to 30% mass variations, 40 m/s wind gusts, 60% changes in ambient brightness, shifting or removing objects from the scene, and people moving aggressively through the drone's visual field. Code, data, and experiment videos can be found on our project page: https://stanfordmsl.github.io/SousVide/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16346
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum
Low, JunEn
Adang, Maximilian
Yu, Javier
Nagami, Keiko
Schwager, Mac
Robotics
Computer Vision and Pattern Recognition
Machine Learning
Systems and Control
We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only onboard perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k image/state-action pairs from an expert MPC with privileged state and dynamics information, randomized over dynamics parameters and spatial disturbances. We then distill this expert MPC into an end-to-end visuomotor policy with a lightweight neural architecture, called SV-Net. SV-Net processes color image, optical flow and IMU data streams into low-level thrust and body rate commands at 20 Hz onboard a drone. Crucially, SV-Net includes a learned module for low-level control that adapts at runtime to variations in drone dynamics. In a campaign of 105 hardware experiments, we show SOUS VIDE policies to be robust to 30% mass variations, 40 m/s wind gusts, 60% changes in ambient brightness, shifting or removing objects from the scene, and people moving aggressively through the drone's visual field. Code, data, and experiment videos can be found on our project page: https://stanfordmsl.github.io/SousVide/.
title SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum
topic Robotics
Computer Vision and Pattern Recognition
Machine Learning
Systems and Control
url https://arxiv.org/abs/2412.16346