The ROBOCART project developed a fully-automatic simulated supermarket cart, named ROBOCART (tracker), to provide customers with a hands-free shopping experience. The system features human-tracking, trajectory prediction, automatic path-planning, and automatic charging capabilities. The project utilized an A* algorithm to plan the cart’s path and compared it with the most optimal path, explaining their design choices. The Kalman-Filter was also integrated into the system to make the customer-following task smarter and demonstrated how it saves up to 13% of the time in certain scenarios.
Path Planning ROS using A*
This environment is supposed to allow path planning and following the human around. After this if the user starts the operation of “To paying area” the robot should be able to go to the paying area. When the battery is low, the robot
Visual path planning (MAP 500x500)
This environment is supposed to allow path planning giving position of human based on camera robot should be following the human around. After this if the user starts the operation of “To paying area” the robot should be able to go to the paying area. When the battery is low, the robot goes to the closest battery station.
Visual path planning with prediction (MAP 500x500)
This environment is supposed to allow path planning giving position of human based on camera robot should be following the human around. In this case we are making a prediction with the Kalman Filter for the future position.
Visual path planning with Obstacles Update (MAP 500x500)
This environment is supposed to allow path planning giving position of human based on camera robot should be following the human around. In this case we are making a prediction with the Kalman Filter for the future position. Objects that appear in real life on the map, should update in the grid map.