Page 48 - AI for Good-Innovate for Impact

AI for Good-Innovate for Impact

The network, equipped with sensors, cameras, communication systems, and payload delivery
mechanisms, collaborates to carry out a range of tasks such as reconnaissance, damage
assessment, communication relay, and aid distribution. Through advanced data collection
and mapping algorithms, the UAV network achieves real-time situational awareness, facilitating
informed decision-making by the response teams. Each UAV maintains a connection to ground
stations, either through direct links or an ad-hoc network, ensuring seamless coordination and
data exchange.

The use case’s goal is to enhance the efficiency of response efforts, increase resilience, and
accelerate recovery in communities affected by disasters. By offering a scalable, adaptable,
and sustainable solution, the use case represents a significant step forward in disaster response
technology.

UN Goals:

• SDG 3: Good Health and Well-being,
• SDG 11: Sustainable Cities and Communities,
• SDG 15: Life on Land

Justify UN Goals selection: The use case enhances the efficiency of the disaster response
system and directly mitigates loss of life and damage to city infrastructure.

Partner name: Turkcell

7�2�2 Future work

Model development, Setup reference tools, notebooks and simulation environment

Elaborate proposal: If the scholarship is awarded, we will utilize the funds to recruit PhD students
dedicated to developing a disaster scenario simulator and designing reinforcement learning
(RL) algorithms for multi-UAV systems to enhance disaster response times. The outcomes of
this work will include an open-source simulator and an environment for algorithm design,
alongside numerical results for the developed algorithms.

7�3� Use case requirements

• REQ-01: It’s critical that drones have the capability to operate autonomously and
collaboratively.
• REQ-02: It’s critical that drones should be able to communicate with each other and with
base stations in real-time.
• REQ-03: It’s critical to implement advanced object detection algorithms to identify
damaged infrastructure and locate survivors.
• REQ-04: It’s critical that drones process and analyze data locally to minimize latency.
• REQ-05: It’s critical to seamlessly integrate data from multiple sources, including drone
cameras and satellite images.
• REQ-06: It’s critical that the system provides a user-friendly interface for disaster response
teams to monitor and control drone operations.
• REQ-07: It’s critical that the system displays real-time data and analytics for informed
decision-making.
• REQ-08: It’s critical that the system optimize drone operations to maximize battery life
without compromising area coverage.

32