Bibliography of AI Portfolios

This repository contains influential references used in all the AI portfolio submissions for "IE 694: Industrial Applications of Artificial Intelligence" coursework that inspired and majorly governed the theoretical and practical portfolio submissions.

Additionally, we also provide the corresponding latex, assets and pdf artifact files for further easing out reference work progress. Also, in below sections the corresponding links for practical work associated with the portfolios are also provided.

Table of Contents

• Exploring Scope of Applying Deep Learning Techniques on 3D Agriculture Data
  • Agriculture Analysis Approaches
  • Deep Learning Analysis Approaches
• Exploring Scope of Using Multi-Agent Reinforcement Learning Systems for Efficient Warehouse Management with Robots
  • Conventional Optimization Approaches
  • Reinforcement Learning Approaches
• Exploring Robustness of Automated Pricing Algorithmic Collusion in Financial Markets
• Citing the Experiments and Theoretical Documents for the submitted AI Portfolios

Exploring Scope of Applying Deep Learning Techniques on 3D Agriculture Data

• Foundational Survey Work: Deep learning–Method overview and review of use for fruit detection and yield estimation, Koirala A. et al. (2019).
• Previous Work: Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging, Stajnko D. et al. (2004).
• Tradtional CV Approaches Survey: A Survey of Computer Vision Methods for Counting Fruits and Yield Prediction, Syal A. et al. (2013).

Agriculture Analysis Approaches

• Preleminary Work: Image segmentation for fruit detection and yield estimation in apple orchards, Bargoti S. et al. (2017).
• Fuji-SfM Dataset: Fuji-SfM dataset: A collection of annotated images and point clouds for Fuji apple detection and location using structure-from-motion photogrammetry, Gené-Mola J. et al. (2017).
• Fuji-SfM's Application System: Fruit detection and 3D location using instance segmentation neural networks and structure-from-motion photogrammetry, Gené-Mola J. et al. (2020).
• PFuji-Size Dataset: PFuji-Size dataset: A collection of images and photogrammetry-derived 3D point clouds with ground truth annotations for Fuji apple detection and size estimation in field conditions, Gené-Mola J. et al. (2021).
• PFuji-Size's Application Work: In-field apple size estimation using photogrammetry-derived 3D point clouds: Comparison of 4 different methods considering fruit occlusions, Gené-Mola J. et al. (2021).

Deep Learning Analysis Approaches

• RandLA-Net for PCLs: Randla-net: Efficient semantic segmentation of large-scale point clouds, Hu Q. et al. (2017).
• Improve Segmentation Model Training: PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies, Qian G. et al. (2022).

Exploring Scope of Using Multi-Agent Reinforcement Learning Systems for Efficient Warehouse Management with Robots

• Foundational Theoretical RL Survey Work: A Review of Cooperative Multi-Agent Deep Reinforcement Learning, OroojlooyJadid A. et al. (2019).

• Foundational RL Implementation Work: Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning, Christianos F. et al. (2020).

Conventional Optimization Approaches

• MAPD with Combined Task Assignment: Integrated Task Assignment and Path Planning for Capacitated Multi-Agent Pickup and Delivery, Chen Z. et al. (2021).

• MAPD Independent of Task Assignment: Lifelong Multi-Agent Path Finding in Large-Scale Warehouses, Li J. et al. (2021).

Reinforcement Learning Approaches

• Dual Reward System for MARLS: MARL-Based Dual Reward Model on Segmented Actions for Multiple Mobile Robots in Automated Warehouse Environment, Lee H. et al. (2022).

• Scalable HNSAC for MARLS: Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers, Krnjaic A. et al. (2022).

Exploring Robustness of Automated Pricing Algorithmic Collusion in Financial Markets

• Algorithmic Collusion Feasibility: Robust Algorithmic Collusion, Eschenbaum N. et al. (2021).

• Baseline Deep Learning Collusion: Algorithmic Collusion: Insights from Deep Learning, Hettich M. (2021).

• Replay Based Collusion: Understanding algorithmic collusion with experience replay, Han B. et al. (2021).

Citing the Experiments and Theoretical Documents for the Submitted AI Portfolios

If you find any of the theoretical work interesting and useful in your research work, please consider citing it with corresponding portfolio citations:

Agriculture Portfolio Citation

@misc{fuji-point-cloud-analysis,
  author = {Rana, Ashish},
  title = {Exploring Scope of Applying Deep Learning Techniques on 3D Agriculture Data},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/arana-initiatives/agro-point-cloud-seg-pipeline}},
}

Manufactoring Portfolio Citation

@misc{manufactoring-marls-case-study,
  author = {Rana, Ashish},
  title = {Exploring Scope of Using Multi-Agent Reinforcement Learning Systems for Efficient Warehouse Management with Robots},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/ashishrana160796/analyzing-cooperative-marls}},
}

Finance Portfolio Citation

@misc{algorithmic-collusion-analysis,
  author = {Rana, Ashish},
  title = {Exploring Robustness of Automated Pricing Algorithmic Collusion in Financial Markets},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/arana-initiatives/boosting-social-dilemma-collusion}},
}