Search Results

In this paper, the design, implementation, and testing of an autonomous agricultural robot with GPS guidance is presented. This robot is also responsible for weed detection and killing by spraying appropriate herbicide as well as fertilizing. This rover is powered by 5 12 V electric bike batteries and two electric motors. Machine learning algorithms such as Haar feature-based cascade classifiers has been utilized to detect three kinds of common weeds found in a corn field. The robot control system consists of GPS guided control of propulsion system and steering actuators, an image processing and detection system, and a spray control system for herbicide and fertilizer applications. Multiple microprocessors such as Raspberry Pi 3, Arduino, as well as an on-board computer have used to provide all control functions in an integrated fashion. Open sources software such as Mission Planner and ReachView have been used to provide autonomous guidance of the vehicle.

Accuracy in detecting a moving object is critical to autonomous driving or advanced driver assistance systems (ADAS). By including the object classification from multiple sensor detections, the model of the object or environment can be identified more accurately. The critical parameters involved in improving the accuracy are the size and the speed of the moving object. All sensor data are to be used in defining a composite object representation so that it could be used for the class information in the core object’s description. This composite data can then be used by a deep learning network for complete perception fusion in order to solve the detection and tracking of moving objects problem. Camera image data from subsequent frames along the time axis in conjunction with the speed and size of the object will further contribute in developing better recognition algorithms.