ZRush – a hybrid control system for robot swarms

chevron-icon
Back
project-presentation-img
Alessandro Longo
Project Owner

ZRush – a hybrid control system for robot swarms

Funding Awarded

$40,000 USD

Expert Review
Star Filled Image Star Filled Image Star Filled Image Star Filled Image Star Filled Image 0
Community
Star Filled Image Star Filled Image Star Filled Image Star Filled Image Star Filled Image 0 (0)

Status

  • Overall Status

    🛠️ In Progress

  • Funding Transfered

    $20,000 USD

  • Max Funding Amount

    $40,000 USD

Funding Schedule

View Milestones
Milestone Release 1
$5,000 USD Transfer Complete TBD
Milestone Release 2
$7,500 USD Transfer Complete TBD
Milestone Release 3
$7,500 USD Transfer Complete TBD
Milestone Release 4
$7,500 USD Pending TBD
Milestone Release 5
$7,500 USD Pending TBD
Milestone Release 6
$5,000 USD Pending TBD

Status Reports

Jan. 29, 2023

Status
🧐 Fair, but could have been better
Summary

We are happy with our progression, currently tackling the hardest problem we encountered so far - creating an accurate map of the environment from orthometric drone images

Full Report

Dec. 9, 2022

Status
😀 Excellent
Summary

We are very happy with the progress we are making, and we are moving steadily towards the final output for round 1.

Full Report

Oct. 24, 2022

Status
🙂 Pretty good
Summary

progress is being made and we are happy for the work done and future plans for the project.

Full Report

Aug. 20, 2022

Status
🙂 Pretty good
Summary

completed milestone 1. 90% to milestone 2 completion.

Full Report

Video Updates

Zrush – Team meeting 8

16 March 2023

Zrush – Team meeting 6

16 March 2023

ZRush – Team meeting 5

16 March 2023

Presentation on delivery of milestone 2

16 March 2023

ZRush – Kickoff presentation

15 March 2023

Project AI Services

No Service Available

Overview

Swarm Robotics is an emerging field of adapting the phenomenon of natural swarms to robotics. It is a study of robots that are aimed to mimic natural swarms, like ants and birds, to form a system that is scalable, flexible, and robust. These robots show self-organization, autonomy, cooperation, and coordination amongst themselves. Benefits of swarms over traditional robotics include fault tolerance, scalability, operational efficiency, and ability to operate in dangerous or hazardous environments. 

We have taken inspiration from popular RTS (real-time strategy) games, such as StarCraft and Age of Empires, which have successfully used swarm intelligence and multi-agent AI systems in the past 20+ years.

ZRush aims to extend the same mechanics and user experience to real-world practical applications by designing a control system for swarms of robots that combines autonomous swarm behaviour with human piloting and decision-making. The control system focusses on precision, reliability, and flexibility and aims at overcoming the issues that currently limit the use of robot swarms in real-life scenarios.

Proposal Description

Compnay Name

ZRush

Problem Description

Swarm robotics is a relatively young field of research and has not yet been widely adopted in industry. As of today, the peculiar properties of swarms make them somewhat unreliable in real-life applications:

  • Unreliability of distributed swarm behaviour algorithms
  • Lack of communication within members of the swarm
  • Difficulty testing in real-world scenarios
  • Relatively high cost of building a swarm

Solution Description

Our solution aims to build an easy to use and accurate control system that allows human operators to manoeuvre large swarms of robots across many environments – We are aiming to minimise reliance on distributed swarm behaviour, focussing instead on human-machine interaction and decision-making.

The ZRush control system will feature an AI system that takes readings from the sensors mounted on the robots to reconstruct a 3D map of the swarm's surroundings and display the map on the interface. This allows human operators to accurately control the swarm through a series of commands, customised to the swarm's abilities.

ZRush will also feature behavioural learning algorithms that will improve swarm behaviour in time by learning from the humans controlling the robots.

Project Benefits for SNET AI platform

In this funding round, we will build and host on the SNET AI platform a Multi-variable 3D AI mapper. 

The Multi-variable 3D AI mapper is not limited to use within robot swarms, but can be used in any application where a full map of the environment must be reconstructed using multiple sensors.

The Multi-variable 3D AI mapper is the core of the ZRush control system. All the communication from the control system to the swarms, and the map reconstruction, will be done through the AI systems hosted on the SNET AI platform.

Real-time mapping will require ZRush to capture and process inputs from a very high number of sensors (at least equal to the number of robots in the swarm), therefore expected API call volume would run in the order of millions.

In future stages of the project, we will be looking to build swarm intelligence behavioural learning algorithms and host them on the SNET AI platform.

Alignment with SNET values

The distinctive properties of robot swarms make them very suitable for a series of use-cases where traditional robotics would be highly inefficient. Many of these use-cases have a very positive humanitarian and environmental impact.

  • Emergency search and rescue missions
  • Precision farming
  • Environmental monitoring
  • Operations in collapsed mines, underwater sites, toxic or radioactive sites, and other dangerous or hazardous locations

Competitive Landscape

Our closest competitors are companies that provide control systems for robots and drones. Examples of such companies are SenseFly and DroneInch, as well as start-ups such as UAVIA and SkyWard.

Although some of these control systems can support multiple bots/drones, none are built to work on a full-scale robot swarm, and don’t incorporate swarm AI.  In addition, these systems are built exclusively for drones and aerial robots, whereas ZRush will provide control systems for aquatic and terrestrial swarms, as well as aerial. 

 We aim to be the first company that provides a control system designed specifically for full-scale robot swarms.

Marketing & Competition

We have a B2B business model that sees us offering a full package of ZRush control system, robot swarms (provided by Partners), and experienced operators as a service.

Partnerships with robotics companies would give us access to a variety of custom-built robot swarms in order to cover a wide range of applications.

 

 

 

Long Description

ZRush aims to build an easy to use, intuitive control system that allows human operators to control large swarms of robots accurately and reliably.

 

The ZRush control system uses a multi-variable 3D AI mapper to render the environment around the swarm into a 3D map that is displayed on the interface. 

The AI mapper will include a number of AI models that each work on a different set of sensors. This will allow ZRush to be compatible with any type of swarm and with any type of sensors mounted on the robots. 

The mapper will:

  • Take N independently moving camera readings, and GPS positioning of each camera (simulating robots equipped with cameras and GPS that move in independent directions)
  • Process the inputs to recreate a 3D map of the view of each camera
  • Combine all the maps into a single map that covers the whole surroundings of the swarm
  • Function in real-time
  • Pinpoint the location of each robot within the map
  • In the future, it will be compatible to other combinations of input sensors
 

 

Through ZRush, human operators will be able to control the full swarm, subsets of the swarm, or single robots. Swarm behaviour algorithms allow multiple robots to be controlled as a single entity.

 

Key Features:

  • Control full swarm, subgroups, or even single robots
  • Behavioural learning of swarm AI
  • Swarm AI to optimise movement and actions when controlling multiple robots
  • Control heterogeneous swarms (composed by different types of robots)
  • Fully customisable to the features and capabilities of specific swarms
  • View real-time status of each robot and identify malfunctioning or broken robots
  • Real-time alert system in response to pre-defined triggers
  • Risk mitigation system to shut down robots that lose communication with ZRush 
  • Set of pre-defined universal swarm action commands (explore target area, explore surroundings, regroup around target point, return to docking station, etc.)

AI Services

Proposal Video

Placeholder for Spotlight Day Pitch-presentations. Video's will be added by the DF team when available.

  • Total Milestones

    6

  • Total Budget

    $40,000 USD

  • Last Updated

    11 Mar 2024

Milestone 1 - Project start

Status
😀 Completed
Description

Signed Contract

Deliverables

Budget

$5,000 USD

Link URL

Milestone 2 - Design - pt1

Status
😀 Completed
Description

Litepaper, website design, logo, brand identity

Deliverables

Budget

$7,500 USD

Link URL

Milestone 3 - AI mapper - pt1

Status
😀 Completed
Description

System architecture, literature review, and data aquisition

Deliverables

Budget

$7,500 USD

Link URL

Milestone 4 - Design - pt2

Status
😐 Not Started
Description

Website creation, UI design for interface

Deliverables

Budget

$7,500 USD

Link URL

Milestone 5 - AI mapper - pt2

Status
😐 Not Started
Description

Model design and training

Deliverables

Budget

$7,500 USD

Link URL

Milestone 6 - AI mapper - pt3

Status
😐 Not Started
Description

Testing and refinements

Deliverables

Budget

$5,000 USD

Link URL

Join the Discussion (0)

Reviews & Rating

New reviews and ratings are disabled for Awarded Projects

Sort by

0 ratings

Summary

Overall Community

0

from 0 reviews
  • 5
    0
  • 4
    0
  • 3
    0
  • 2
    0
  • 1
    0

Feasibility

0

from 0 reviews

Viability

0

from 0 reviews

Desirabilty

0

from 0 reviews

Usefulness

0

from 0 reviews