Abstract
In this paper, a study of the odometric system for the autonomous cart Verdino, which is an electric vehicle based on a golf cart, is presented. A mathematical model of the odometric system is derived from cart movement equations, and is used to compute the vehicle position and orientation. The inputs of the system are the odometry encoders, and the model uses the wheels diameter and distance between wheels as parameters. With this model, a least square minimization is made in order to get the nominal best parameters. This model is updated, including a real time wheel diameter measurement improving the accuracy of the results. A neural network model is used in order to learn the odometric model from data. Tests are made using this neural network in several configurations and the results are compared to the mathematical model, showing that the neural network can outperform the first proposed model.
Highlights
Odometry is one of the basic localization systems in any autonomous vehicle [1,2]
The main contribution of this paper is the application of a sensor set, including real time wheel diameter measurement to improve the accuracy of the odometric system for a golf cart, or similar
This paper is centered in the odometric system of the autonomous cart Verdino and the solutions applied in order to increase its accuracy
Summary
Odometry is one of the basic localization systems in any autonomous vehicle [1,2]. It is based on the use of data from on-board sensors in order to estimate changes in position and orientation from the vehicle itself, and is subsequently used in many autonomous systems to estimate their position relative to a starting location, by integrating sensors measurements. Some problems like the home position of steering angle and non-linearity between steering wheel and steering angle reduce its applicability to improving odometric accuracy With this sensor, the model for obtaining a position based on speed and steering angle is worse than a badly calibrated odometry, so the authors have discarded it in order to improve odometry. The main contribution of this paper is the application of a sensor set, including real time wheel diameter measurement to improve the accuracy of the odometric system for a golf cart, or similar.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
