New artificial intelligence based tire size identification for fast and safe inflating cycle
- Authors: Kahandawa, Gayan , Choudhury, Tanveer , Ibrahim, Yousef , Dzitac, Pavel , Mazid, Abdul Md
- Date: 2015
- Type: Text , Conference proceedings
- Full Text: false
- Description: Motor vehicle accidents are one of the main killers on the road. Modern vehicles have several safety features to improve the stability and controllability. The tire condition is critical to the proper function of the designed safety features. Under or over inflated tires adversely affects the stability of vehicles. It is generally the vehicle's user responsibility to ensure the tire inflation pressure is set and maintained to the required value using a tire inflator. In the tire inflator operation, the vehicle's user sets the desired value and the machine has to complete the task. During the inflation process, the pressure sensor does not read instantaneous static pressure to ensure the target value is reached. Hence, the inflator is designed to stop repetitively for pressure reading and avoid over inflation. This makes the inflation process slow, especially for large tires. This paper presents a novel approach using artificial neural network based technique to identify the tire size. Once the tire size is correctly identified, an optimized inflation cycle can be computed to improve performance, speed and accuracy of the inflation process. The developed neural network model was successfully simulated and tested for predicting tire size from the given sets of input parameters. The test results are analyzed and discussed in this paper. © 2015 IEEE.
Optimal sensing requirement for slippage prevention in robotic grasping
- Authors: Dzitac, Pavel , Mazid, Abdul Md , Ibrahim, Yousef , Appuhamillage, Gayan , Choudhury, Tanveer
- Date: 2015
- Type: Text , Conference proceedings
- Full Text: false
- Description: This paper presents a new theoretical development and modelling related to the requirement of the minimum number of sensors necessary for slippage prevention in robotic grasping. A fundamental experimental investigation has been conducted to support the newly developed postulate. A series of basic experiments proved that it is possible to evaluate the contributions of various sensors to slippage prevention and control in robotic grasping. The use of three discrete physical sensors, one for each of the three sensing functions (normal, tangential and slippage), has been proven to be the most reliable combination for slippage prevention in robotic grasping. It was also proven that the best performance from a two-sensor combination can be achieved when normal grasp force and tangential force are both monitored in the grasping process. © 2015 IEEE.