A model is developed using UNet with the help of Convolution Neural Networks that takes a chest x-ray image as input and predicts whether the given image has a pneumothorax or not.
This environment makes use of a camera system equipped on the wrist of both the master and the slave robot, and uses OpenCV for detecting the contour of the target object. This information is then used by the RL agent for learning optimal policies for making both the robots reach the target.
Two UR5 robots reach targets specified within their own workspace and coordinate at a common point using Reinforcement Learning
Designing an RL agent for the actuator of the PSM machine to reach the parcel position in the most optimum way.
Here two UR5 robots are coordinated using planning pipelines from ROS Moveit to execute a pick-and-place type scenario.
A linear and non-linear controller were designed for a bioreactor system to control the flow of glucose into the substrate for producing biomass.
A UR5 robot arm is trained using Proximal Policy Optimization (PPO) to reach 5 random targets defined in the environment and is evaluated on three new targets.
Classical ML models such as logistic regression, random forest and gradient boosting are used to train on cat-in-the-dat dataset.