Skip to content
View pranaypalem's full-sized avatar

Block or report pranaypalem

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pranaypalem/README.md

💫 About Me

👋 Hi, I’m @pranaypalem
🧠 AI & Robotics Engineer passionate about building autonomous systems that adapt, learn, and scale
🚀 I specialize in Reinforcement Learning, Robotic Perception, and MLOps pipelines for end-to-end machine learning lifecycle management
🛠 Currently working on deploying scalable deep learning models in real-world robotic and healthcare environments


🧠 Machine Learning & AI

  • Built and deployed deep learning models (Faster R-CNN, YOLOv8, ResNet) for healthcare and robotic vision
  • Applied self-supervised techniques like SimCLR and BYOL on medical datasets (NIH Chest X-rays, Mammo)
  • Trained RL agents (PPO, TRPO, SAC) in Isaac Lab, MuJoCo, and OpenAI Gym for continuous control and motion planning
  • Used Grad-CAM, attention maps, and class re-weighting for explainability and imbalance handling
  • Integrated model tuning, augmentation, and real-time inference optimization using PyTorch/TensorFlow + TensorRT

⚙️ MLOps & Model Deployment

  • 🚢 Deployed models in production using Docker, AWS SageMaker, and TensorRT
  • 🧪 Tracked experiments with MLflow, managed data & model versioning via DVC and DagsHub
  • 🌀 Orchestrated ML pipelines using Apache Airflow + Astronomer
  • 🔁 Automated CI/CD with GitHub Actions, ensuring robust model updates and testing
  • 📈 Monitored live inference metrics using Grafana + PostgreSQL dashboards
  • 🧠 Built ETL + NLP pipelines with HuggingFace and deployed transformer models in real-world workflows

🤖 Robotics & Simulation

  • Developed full-stack robotic systems integrating LiDAR-based SLAM, RRT exploration, and object detection (YOLOv8)
  • Simulated dynamic robotic agents using Isaac Sim, Isaac Lab, and MuJoCo (DeepMind)
  • Designed quaternion-based foldable robots and improved sim-to-real performance using scikit-optimize
  • Integrated navigation and control pipelines using ROS 2, MoveIt 2, Nav2, and URDF
  • Deployed Jetson-based inference pipelines with sub-50ms latency
  • Developed interactive robotic systems in Unity for perception and control prototyping

🧰 Tech Stack

🧠 AI / ML

PyTorch TensorFlow scikit-learn SimCLR Keras Huggingface

⚙️ MLOps & Deployment

MLflow DVC DagsHub Airflow SageMaker Grafana PostgreSQL Docker GitHub Actions

🤖 Robotics & Perception

ROS 2 MoveIt 2 Nav2 Isaac Sim Isaac Lab MuJoCo YOLOv8 OpenCV Unity TensorRT

🧮 Programming & Data

Python C++ NumPy Pandas Matplotlib Plotly


🌐 Socials

LinkedIn Medium Gmail GitHub


🚀 Project Showcase

Simulated and optimized foldable robot configurations in MuJoCo using adaptive kinematics, servo dynamics, and control tuning for real-world robustness.

Designed an optimization pipeline to identify and tune dynamic parameters of MuJoCo robots for improved sim-to-real accuracy.

Benchmarked PPO and TRPO algorithms using Stable-Baselines3 in OpenAI Gym for continuous robotic control, achieving stable training with 250+ episodic reward.


📊 GitHub Stats




Pinned Loading

  1. foldable-robotics foldable-robotics Public

    A foldable robotics project inspired by basilisk lizard locomotion, featuring four-bar mechanism design, MuJoCo simulations, and adaptive movement optimization.

    Jupyter Notebook 1

  2. RL-ppo-vs-trpo RL-ppo-vs-trpo Public

    A repository comparing Proximal Policy Optimization (PPO) and Trust Region Policy Optimization (TRPO) algorithms through implementation and performance evaluation in reinforcement learning environm…

    Jupyter Notebook 1

  3. artificial-potential-field artificial-potential-field Public

    A multi-robot firefighting system that uses Artificial Potential Field (APF) controllers to autonomously navigate robots, extinguish fires, avoid obstacles, and manage energy efficiently.

    Jupyter Notebook

  4. mujoco-parameter-identification mujoco-parameter-identification Public

    This repository compares real-life oscillation data from Tracker with MuJoCo simulations to estimate and identify the stiffness and damping characteristics of a cardstock material.

    Jupyter Notebook 1

  5. kinematics-analysis kinematics-analysis Public

    This repository will contain a bunch of kinematic analysis on various robots. Some are robots with a four bar mechanism for a leg, and some are foldable robots

    Jupyter Notebook 1

  6. yolov8_tensorrt_docker yolov8_tensorrt_docker Public

    Docker container for high-speed YOLOv8 inference using TensorRT, integrated with ROS Noetic. Supports GPU/CPU fallback, automatic model optimization, and deployment on Jetson and GPU servers.

    Dockerfile 1