Professional Documents
Culture Documents
Robotics Assignment
Robotics Assignment
ROBOTICS ASSIGNMENT
BY:
TASK 1
Problem Statement:
Illegal poaching poses a significant threat to endangered wildlife populations in protected areas,
leading to a decline in biodiversity and ecosystem degradation. Current anti-poaching efforts
often face challenges in effectively monitoring large and remote wildlife habitats, resulting in
difficulties detecting and deterring poaching activities in a timely manner.
Summary:
The problem revolves around combating illegal poaching activities in protected wildlife areas
through the use of drone-based surveillance. The application aims to address the challenges of
monitoring large and remote habitats, detecting poaching incidents in real-time, and deterring
illegal activities through timely intervention. Key requirements include real-time surveillance,
long-range coverage, detection accuracy, autonomous operation, resilience to weather
conditions, seamless data transmission, cost-effectiveness, and minimizing environmental
impact. By leveraging advanced drone technology, the application seeks to enhance anti-
poaching efforts, protect endangered species, and preserve biodiversity in vulnerable
ecosystems.
TASK 2
Research papers:
1. "A Drone-based Anti-Poaching System Using Convolutional Neural Networks"
Summary: This research paper proposes a drone-based anti-poaching system that utilizes
Convolutional Neural Networks (CNNs) for detecting poachers in wildlife reserves. The system
integrates drones equipped with cameras and thermal sensors to capture images of the
environment, which are then analyzed using CNNs to identify humans and potential poaching
activities.
Key Features:
● Utilizes CNNs for object detection and classification, specifically trained to recognize
humans and distinguish them from other animals or objects.
● Employs thermal sensors to enhance detection capabilities, especially in low-light
conditions or dense vegetation where visual imagery may be limited.
● Demonstrates high accuracy in detecting humans and identifying suspicious activities,
enabling timely intervention by anti-poaching patrols.
TASK 3
- Step 2: Analyze the digital map in conjunction with historical poaching data, wildlife migration
patterns, and other relevant factors to identify high-risk areas for poaching activities. Consider
factors such as proximity to roads or settlements, terrain accessibility, vegetation cover, and
known wildlife migration routes or breeding grounds.
- Step 3: Divide the entire reserve into multiple patrol zones or sectors, assigning priority levels
to each zone based on the assessed likelihood of poaching activity. Higher priority zones should
receive more frequent and intensive surveillance. Ensure comprehensive coverage of the entire
reserve area, with no gaps or blind spots.
- Step 4: Plan and optimize patrol routes within each zone, taking into account factors such as
terrain complexity, vegetation density, battery life of drones, and the need for overlapping
coverage to minimize blind spots. Utilize algorithms or software tools for route optimization and
efficient patrol planning.
- Step 5: Deploy a fleet of drones equipped with high-resolution cameras, thermal imaging
sensors, GPS navigation systems, and long-range communication capabilities. The drones
should be designed for extended flight times and capable of operating in various weather
conditions and terrain types.
- Step 6: Program the drones with the pre-planned patrol routes and schedules for each patrol
zone. Implement autonomous flight control systems that enable the drones to follow their
assigned routes with minimal human intervention, while also allowing for manual override or
real-time adjustments as needed.
- Step 7: Integrate advanced obstacle avoidance algorithms and sensors (e.g., LiDAR, radar)
into the drone systems to enable safe navigation through complex terrain, avoiding collisions
with obstacles such as trees, cliffs, or other terrain features.
- Step 8: Implement fail-safe mechanisms and contingency plans for situations such as
communication loss, low battery, or system failures. This could include automated return-to-
base protocols, emergency landing procedures, or redundant communication channels.
- Step 10: Employ advanced computer vision and deep learning algorithms for object detection,
classification, and tracking within the captured imagery and sensor data. These algorithms
should be trained to accurately identify humans, vehicles, and other relevant objects or activities
associated with poaching.
- Step 11: Integrate facial recognition technology and databases of known poachers or
individuals associated with illegal activities. Cross-reference any detected individuals against
these databases for potential identification and flagging of high-risk individuals.
- Step 12: Implement pattern recognition and anomaly detection algorithms to identify
suspicious activities or behaviors that may indicate poaching, such as unusual movements,
gathering of people, or the presence of weapons or hunting equipment.
- Step 13: Continuously monitor the drone telemetry data, sensor outputs, and analysis results
in real-time from a central command center or monitoring station.
- Step 14: Establish predefined rules and thresholds for triggering alerts or notifications based
on the detected activities or anomalies. For example, an alert may be triggered if a certain
number of individuals are detected in a high-risk area or if known poachers are identified.
- Step 15: Upon detection of a potential poaching incident, immediately alert and notify the anti-
poaching teams or law enforcement agencies. Provide them with detailed information, including
GPS coordinates, live video feeds, thermal imagery, and any relevant intelligence gathered from
the drone surveillance.
- Step 16: Coordinate and guide rapid response efforts by ground patrols or intervention teams,
providing them with real-time situational awareness and updates from the drone surveillance.
The drones can also be used to track the movements of the suspected poachers and provide
aerial support during the response operation.
- Step 17: Continuously update and refine the patrol plans, risk assessments, and detection
algorithms based on the experiences and feedback from the field operations. Incorporate new
data and intelligence to improve the overall effectiveness of the anti-poaching surveillance
system.
[2] Nagendra, H., Rocchini, D., Ghate, R., Sharma, B., & Munroe, D. K. (2014). Satellite-Based
Monitoring of Environmental Dynamics in the Hindu Kush-Himalayan Region. In E. M. Younis
(Ed.), Mapping Environmental Dynamics (pp. 87-113). Springer Netherlands.
[3] Plumptre, A. J., Fuller, R. A., Mqsini, A., Andrisoa, P., Narengo, S., Traylor-Holzer, K., ... &
Fa, J. E. (2014). Efficiently combating wildlife crime. In B. Zarin (Ed.), Conservation for the
Anthropocene Ocean (pp. 161-192). Academic Press.
[4] Haines, A. M., Tewes, M. E., Laack, L. L., Horne, J. S., & Young, J. H. (2006). A habitat-
based population viability analysis for ocelots (Leopardus pardalis) in the United States.
Biological Conservation, 132(4), 424-436.
[5] Zięba, S., Więcek, P., & Wojciechowski, D. (2022). Optimization of patrol routes by means of
the multi-criteria genetic algorithm. Information, 13(4), 194.
[6] Sharma, A., Jha, P. C., & Dube, R. (2022). Multi-objective optimization for patrolling multiple
regions using unmanned aerial vehicles. Applied Intelligence, 52(2), 1564-1587.
[7] Lin, S., & Kernighan, B. W. (1973). An effective heuristic algorithm for the traveling-salesman
problem. Operations Research, 21(2), 498-516.
[8] Applegate, D. L., Bixby, R. E., Chvatal, V., & Cook, W. J. (2006). The traveling salesman
problem: a computational study. Princeton University Press.
[9] Mulero-Pázmány, M., Stoldt, M., Van Essen, L. D., Negro, J. J., & Sassen, T. (2014).
Remotely piloted aircraft systems as a rhinoceros anti-poaching tool in Africa. PLoS One, 9(1),
e83873.
[10] Gonzalez, L. F., Montes, G. A., Puig, E., Johnson, S., Mengersen, K., & Gaston, K. J.
(2016). Unmanned aerial vehicles (UAVs) and artificial intelligence revolutionizing wildlife
monitoring and conservation. Sensors, 16(1), 97.
[11] Yin, L., Savvaris, A., Masiar, A., & Tsourdos, A. (2022). A review on vision-based drone
navigation and obstacle avoidance. Sensors, 22(9), 3509.
[12] Dhiman, N., & Crespo, L. G. (2022). A review of autonomous obstacle avoidance
approaches for unmanned aerial vehicles. IEEE Access, 10, 10818-10846.
[13] FAA (2021). Unmanned Aircraft Systems (UAS). Federal Aviation Administration.
[14] EASA (2022). Unmanned Aircraft Systems (UAS). European Union Aviation Safety Agency.
[15] Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020). Deep
learning for generic object detection: A survey. International Journal of Computer Vision, 128(2),
261-318.
[16] Zou, Z., Shi, Z., Guo, Y., & Ye, J. (2019). Object detection in 20 years: A survey. arXiv
preprint arXiv:1905.05055.
[17] Ngan, M. L., Grother, P. J., Hanaoka, K., Kansaku, K., & Martelli, C. (2021). Ongoing Face
Recognition Vendor Test (FRVT). NIST Interagency/Internal Report (NISTIR), 8280.
[18] Phillips, P. J., Wechsler, H., Huang, J., & Rauss, P. J. (1998). The FERET database and
evaluation procedure for face-recognition algorithms. Image and Vision Computing, 16(5), 295-
306.
[19] Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM
Computing Surveys (CSUR), 41(3), 1-58.
[20] Pimentel, M. A., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014). A review of novelty
detection. Signal Processing, 99, 215-249.
[21] Mulero-Pázmány, M., Jenni-Eiermann, S., Strebel, N., Sattler, T., Negro, J. J., & Tablado,
Z. (2017). Unmanned aircraft systems as a new source of disturbance for wildlife: A systematic
review. PLoS One, 12(6), e0178448.
[22] Moro, M., Haque, A. N., Hicks, C., Bakiu, R., Shrestha, S., & Chhetri, B. B. K. (2021).
Application of drones for wildlife monitoring and conservation in Nepal. Remote Sensing, 13(22),
4535.
python
import geopandas as gpd
import folium
import cv2
import numpy as np
from sklearn.cluster import DBSCAN
from collections import Counter
from datetime import datetime