Bio!
I am a Ph.D. Candidate in Computer Science at the University of Memphis, advised by Dr. Myounggyu Won. I obtained my MS in Computer Science in May 2022 and my B.Sc. in Computer Science & Engineering in May 2015 from the University of Memphis, USA, and the University of Dhaka, Bangladesh, respectively. Before joining the Ph.D. program, I worked as a software engineer at Samsung R&D Institute Bangladesh and as a Senior Officer in the Information and Communication Technology Division at Argani Bank PLC.
Technical Skills
- Language & Tools: Python, C/C++, Javascript, PyTorch, TensorFlow, NumPy, Scikit-learn, Pandas, matplotlib, MATLAB, Version Control (Git), LaTeX, Linux,
- Machine Learning: Deep Learning, Reinforcement Learning, Supervised and Unsupervised Learning, Classification, Regression, Generative Models, CNN, LSTM,RNN, Time series forecasting
- Simulators: SUMO, CARLA, OpenAI Gym, Veins
Research Interests
Intelligent Transportation Systems | Conntected and Autonomous Vehicles | Self-Driving Cars | Machine Learning | Reinforcement Learning | Computer Vision | Speech Emotion Recognition
I am looking for a research scientist position in the areas of robotics, self-driving vehicles, autonomous systems, connected and autonomous vehicles, and machine learning. I am also open to a full-time position in the following areas:
- Research Scientist in Artificial Intelligence, Machine Learning, Reinforcement Learning
- Artificial Intelligence (AI), Machine Learning (ML), and Reinforcement Learning Engineering
- Data Scientist / Data Engineering
- Software Engineering / Software Engineering Focused on Machine Learning
News
Education
- Ph.D. in Computer Science, University of Memphis (Graduation: May 2024)
- Master's in Computer Science, University of Memphis, May 2022
- Bachelor of Science in Computer Science & Engineering, University of Dhaka, 2015
Research
My current research focuses on a machine learning-driven approach for a next-generation intelligent traffic control system for autonomous vehicles (AVs), aiming to reduce traffic congestion and enhance driving safety. The next-generation traffic control system consists of i) an intelligent adaptive cruise control system (ACC) and ii) a V2X-based cooperative intelligent lane-change system. The intelligent ACC system facilitates the AVs in adaptively adjusting the inter-vehicle gap to optimize traffic efficiency and driving safety under complex, dynamically changing, and diverse traffic conditions with a high degree of uncertainties caused by human-driven vehicles (HVs). The cooperative lane-change system, combined with the intelligent ACC system, will enable AVs to make an optimal lane-change decision based on microscopic and macroscopic traffic information received via V2X, thereby maximizing traffic flow, driving safety, and passenger comfort. I have been using deep reinforcement learning algorithms (e.g., DQN, DDPG, PPO, etc.) to generate fine-grained motion control for AVs in lateral and longitudinal directions in response to dynamically changing traffic conditions on various road types, including highways with ramps.
Intelligent Adaptive Cruise Control (Publications at ICML, ICRA)
Cooperative multi-agent Lane Change
Platoon (Publications at IROS)
Pedestrian Crossing Intention (Publications at IROS)
Adptive Vehicle Position Control (Publications at ITSC)
Publications
[1] Yadavalli, Sushma Reddy, Lokesh Chandra Das, and Myounggyu Won. "RLPG: Reinforcement Learning Approach for Dynamic Intra-Platoon Gap Adaptation for Highway On-Ramp Merging. International Conference on Intelligent Robots and Systems (IROS), 2023
[2] Abbasi, Jibran Ali, Navid Mohammad Imran, Lokesh Chandra Das, and Myounggyu Won. "Watchped: Pedestrian crossing intention prediction using embedded sensors of smartwatch. International Conference on Intelligent Robots and Systems (IROS), 2023
[3] Das, Lokesh Chandra, Dipankar Dasgupta, and Myounggyu Won. "LSTM-Based Adaptive Vehicle Position Control for Dynamic Wireless Charging." International Conference on Intelligent Transportation Systems (ITSC), 2023.
[4] Das, Lokesh Chandra, and Myounggyu Won. "Saint-acc: Safety-aware intelligent adaptive cruise control for autonomous vehicles using deep reinforcement learning." International Conference on Machine Learning (ICML), 2021
[5] Das, Lokesh, and Myounggyu Won. "D-ACC: Dynamic Adaptive Cruise Control for Highways with Ramps Based on Deep Q-Learning." IEEE International Conference on Robotics and Automation (ICRA), 2021
[6] Das, Lokesh Chandra, Muhammed Tawfiqul Islam, and Syed Faisal Hasan. "A Generalized Internet of Things (IoT) Framework for Serving Multiple Applications." International Conference on Internet Applications, Protocols and Services (NETAPPS2015), 2015
Preprint
[1] Das, Lokesh Chandra, and Myounggyu Won. "LCS-TF: Multi-Agent Deep Reinforcement Learning-Based Intelligent Lane-Change System for Improving Traffic Flow"
Teaching
- COMP 4272/6272: System Administration and UNIX Programming
- COMP 1900 - Introduction to Programming (Python) -Lab (Spring 2023)
- COMP 3825 - Networking and Information Assurance (Fall 2022)
- COMP 7/847 - Adv. Topic in Machine Learning (Fall 2022)
- COMP 7745 - Machine Learning (Summer 2022)
- COMP 2150 - Data Structure and Object-Oriented Programming (Summer 2022)
- COMP 7745 - Machine Learning (Spring 2022)
- COMP 7012 - Foundation of Software Engineering (Spring 2022)
- COMP 4/6151 - Introduction to Data Science (Fall 2021)
- COMP 7130 - Information Retrieval and Web Search(Fall 2021)
Honors & Awards
Fellowship
- Carnegie R1 Doctoral Fellowship in Computer Science, University of Memphis (2019-2021)
Graduate Assistantships
- Graduate Teaching Assistantship, Department of Computer Science, University of Memphis (Fall 2021- Present)
Travel Grants
- Graduate Student Association (GSA) Travel Grant, The University of Memphis (2023)
- Graduate Student Association (GSA) Travel Grant, The University of Memphis (2023)
- College of Arts and Science Travel Grant, The University of Memphis (2023)
- IROS Travel Grant, 2023
Projects
Research Projects
- Intelligent Adaptive Cruise Control Systems
- Multi-agent Lance Change
- Dynamic Intra-Platoon Gap Adaption
- Pedestrian Cross Intention Predictions
Personal Projects
- Traffic Volume Prediction using Memory-Based Recurrent Neural Network
- Effect of Length of Skip-Connection of ResNet on its Model Complexity
- Image Classification using Deep Convolution Neural Network
- Multi-Agent Pac-Man Game
- Movie Recommender System