You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.
ROS workspace that creates a trajectory for a UAV to follow passing through a set of given waypoints and avoiding a set of given cylindrical obstacles.
My goal is to come up with a simple and a basic model of an obstacle avoiding bot with the best possible algorithm to detect and avoid an obstacle using only One Ultrasonic Sensor module (HCSR04) and 2 wheels. The project is still into development to find even better an algorithm to achieve the same task.
This Arduino code utilizes an ultrasonic sensor to measure distances. When an object is detected within a fix distance , the connected motors trigger a sequence: move backward, turn right, turn left, then move forward. Motor control is achieved using the AFMotor library, and the distance calculation is based on the sensor's pulse duration.
ENPM 661 Project 3 Phase 2: A rigid robot traverses through a configuration space to find the goal node using A star search algorithm, while it avoid the obstacles in the map