Scribd
Upload
46 views6 pages

Vision Based Autonomous Navigation in GPS-denied Environments

Vision based autonomous navigation is being developed to allow autonomous robots and systems to navigate without GPS in GPS-denied environments. The researcher aims to develop visual-inertial odometry (VIO) and visual simultaneous localization and mapping (VSLAM) to enable navigation using only vision sensors. Over 15 months, milestones include comparing state-of-the-art VIO and VSLAM techniques, implementing them on robots, and integrating the techniques to allow fully autonomous visual navigation of quadcopters and mobile robots without GPS. Potential partners include government agencies and companies in logistics and delivery that use autonomous vehicles.

Uploaded by

Ravi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
46 views6 pages

Vision Based Autonomous Navigation in GPS-denied Environments

Vision based autonomous navigation is being developed to allow autonomous robots and systems to navigate without GPS in GPS-denied environments. The researcher aims to develop visual-inertial odometry (VIO) and visual simultaneous localization and mapping (VSLAM) to enable navigation using only vision sensors. Over 15 months, milestones include comparing state-of-the-art VIO and VSLAM techniques, implementing them on robots, and integrating the techniques to allow fully autonomous visual navigation of quadcopters and mobile robots without GPS. Potential partners include government agencies and companies in logistics and delivery that use autonomous vehicles.

Uploaded by

Ravi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Vision based Autonomous

Navigation in GPS-denied
Environments
R E S E A R C H E R : S U D H I R P R ATA P YA D AV ( R E S E A R C H E N G I N E E R T I H - I H U B D R I S H T I )
M E N T O R S : P R O F. R A J E N D R A N A G A R A N D P R O F. S U R I L V. S H A H ( T I H C O - O R D I N AT O R S
O F V E RT I C A L O N A U T O N O M O U S S Y S T E M S )
Rise of Autonomous Robots
Increasingly, use of autonomous mobile robots is becoming ubiquitous in fields ranging from
logistics, agriculture to defence. They are used for various purposes like surveillance, Mapping,
Delivery of packages etc. We are becoming integrated and dependent on this new technology. 

Underwater Structure
Agriculture Defense Delivery
Surveillance

Cargo in difficult
Warehouse Space Exploration Remote Patient Care
Data Bridge Market Research Terrain
GPS Vulnerabilities
Today almost all navigation systems use GPS (even for local navigation), but GPS is not a reliable technology.
Operating Environment: Atmospheric interference, Indoor & other GPS-denied areas
Deliberate Attacks: as GPS is external to robot it can be hacked/interfered by adversaries (in case of attack/war or other such
situations)

Atmospheric Indoor Forest


Interference Environment Environment

Therefore, autonomous systems need capability to navigate even without GPS if we want to
depend on them in critical situations.
Objective
Developing vision based autonomous navigation for autonomous systems.
VIO: Visual-Inertial Odometry

VSLAM: Visual-SLAM Vision Based Navigation


Milestones and Time-Line (15 months)
July -
Oct – Dec Jan – Aril – June Oct – Dec
Milestones 2020 March 2021 2021
September
2021
2021

Literature review M1

Setting up Hardware for experiments M2

Comparison of various state-of-the art Visual-Inertial Odometry M3


Techniques by Implementing them of hand-held camera

Implementing VIO on quadcopter and mobile robot  M4

Demonstration of visual-inertial-odometry by navigating quadcopter M5


without GPS using remote controlled by pilot
Comparison of various state-of-the art V-SLAM and Navigation M6
Techniques by implementing them on quadcopter and mobile robot
Developing Framework for integrating VIO and V-SLAM for Navigation M7

Implementation of Visual Navigation on quadcopter and mobile robot M8


Potential Partners
Government: DRDO, ISRO
Industry:
◦ E-commerce: Amazon, Flipkart, Reliance
◦ Food-Delivery: Zomato, Swiggy

You might also like