File:The Swift AI system for fast racing drones.webp
From Wikimedia Commons, the free media repository
Jump to navigation
Jump to search
![File:The Swift AI system for fast racing drones.webp](https://upload.wikimedia.org/wikipedia/commons/thumb/c/cb/The_Swift_AI_system_for_fast_racing_drones.webp/800px-The_Swift_AI_system_for_fast_racing_drones.webp.png?20231015210554)
Size of this PNG preview of this WEBP file: 800 × 577 pixels. Other resolutions: 320 × 231 pixels | 640 × 462 pixels | 1,024 × 738 pixels | 1,280 × 923 pixels | 2,148 × 1,549 pixels.
Original file (2,148 × 1,549 pixels, file size: 223 KB, MIME type: image/webp)
File information
Structured data
Captions
Captions
From the study "Champion-level drone racing using deep reinforcement learning"
Summary
[edit]DescriptionThe Swift AI system for fast racing drones.webp |
English: "Swift consists of two key modules: a perception system that translates visual and inertial information into a low-dimensional state observation and a control policy that maps this state observation to control commands. Control commands specify desired collective thrust and body rates, the same control modality that the human pilots use. a, The perception system consists of a VIO module that computes a metric estimate of the drone state from camera images and high-frequency measurements obtained by an inertial measurement unit (IMU). The VIO estimate is coupled with a neural network that detects the corners of racing gates in the image stream. The corner detections are mapped to a 3D pose and fused with the VIO estimate using a Kalman filter. b, We use model-free on-policy deep RL to train the control policy in simulation. During training, the policy maximizes a reward that combines progress towards the centre of the next racing gate with a perception objective to keep the next gate in the field of view of the camera. To transfer the racing policy from simulation to the physical world, we augment the simulation with data-driven residual models of the vehicle’s perception and dynamics. These residual models are identified from real-world experience collected on the race track. MLP, multilayer perceptron." |
Date | |
Source | https://www.nature.com/articles/s41586-023-06419-4 |
Author | Authors of the study: Elia Kaufmann, Leonard Bauersfeld, Antonio Loquercio, Matthias Müller, Vladlen Koltun & Davide Scaramuzza |
Licensing
[edit]![w:en:Creative Commons](https://upload.wikimedia.org/wikipedia/commons/thumb/7/79/CC_some_rights_reserved.svg/90px-CC_some_rights_reserved.svg.png)
![attribution](https://upload.wikimedia.org/wikipedia/commons/thumb/1/11/Cc-by_new_white.svg/24px-Cc-by_new_white.svg.png)
This file is licensed under the Creative Commons Attribution 4.0 International license.
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
File history
Click on a date/time to view the file as it appeared at that time.
Date/Time | Thumbnail | Dimensions | User | Comment | |
---|---|---|---|---|---|
current | 21:05, 15 October 2023 | ![]() | 2,148 × 1,549 (223 KB) | Prototyperspective (talk | contribs) | Uploaded a work by Authors of the study: Elia Kaufmann, Leonard Bauersfeld, Antonio Loquercio, Matthias Müller, Vladlen Koltun & Davide Scaramuzza from https://www.nature.com/articles/s41586-023-06419-4 with UploadWizard |
You cannot overwrite this file.
File usage on Commons
The following page uses this file:
Hidden category: