Ammar N. Abbas

FoundationPoseROS2. FoundationPoseROS2 is a ROS2-integrated system for 6D object pose estimation and tracking, based on the FoundationPose architecture. It uses RealSense2 with the Segment Anything Model 2 (SAM2) framework for end-to-end, model-based, real-time pose estimation and tracking of novel objects.

sim2real-ur-gym-gazebo. Universal Robot Environment for OpenAI Gymnasium and ROS Gazebo Interface

Predictive-Maintenance-BC-IOHMM-DRL. Hierarchical Framework for Interpretable Deep Reinforcement Learning Based- Predictive Maintenance (Applied to NASA Turbofan engine dataset)

aruco-cube-pose-tracking-ros. Python

human_model_gazebo_ros_control. Human Model in Gazebo and Control through ROS

Meg-Pi. Communication between Arduino and Raspberry-pi using SIMULINK: Using Arduino as the sensor for Raspi to perform the fuzzy logic task on real hardware. Simulink is used for serial communication between Arduino and Raspberry-Pi with the external mode deploying code directly on the boards. Figure a: Arduino serial transmit and receive model with pot input and motor control as output. Figure b: Raspberry-pi serial transmit and receive for taking input for processing using fuzzy logic and transmitting output. Fuzzy logic is used further as a Simulink block to perform washing machine control task on real hardware. Here is the link to the youtube video: https://youtu.be/aJTeD2Hq_-o

CoL-SDRPRL. Specialized Deep Residual Policy Reinforcement Learning with Cycle of Learning for Continuous State-Action Spaces: A Case Study on the Tennessee Eastman Process

carla_auto_navigation. Autonomous Navigation Package for Carla-ROS bridge

Practical_RL-coursera. My Solution to the Programming Assignments for Practical Reinforcement Learning from Coursera