Haider N.G.,NED UET |
Karim A.,PCSIR Laboratories Complex
2013 3rd IEEE International Conference on Computer, Control and Communication, IC4 2013 | Year: 2013
Various AI algorithms exist that can serve vehicle autonomy domain within limits and present different critical levels of time-space complexity in real time scenarios. This paper evaluates the performance of WISARD-net for autonomous vehicle vision based maneuver control system for road-following and obstacle avoidance tasks. A novel Grid-WISARD algorithm is proposed and examined for obstacle avoidance maneuver. The vehicle is trained for a small stretch of artificial road with a 3 to 4 sets of road images and achieved successful road-tracking, obstacle avoidance and driving on the left-side of the road. Whereas ANN models normally require long training, the proposed model was able to demonstrate successful maneuvers with comparatively considerably few training samples and training duration. © 2013 IEEE.
Iqbal J.,COMSATS Institute of Information Technology |
Iqbal J.,Aalto University |
Riaz un Nabi S.,NED UET |
Attayyab Khan A.,King Faisal University |
Khan H.,Italian Institute of Technology
Life Science Journal | Year: 2013
This paper presents a novel robotic framework to help students to practically grasp the concepts of Robotics and Control Systems in a laboratory environment. The framework is centered on a robotic rover having two tank-like tracks which permit locomotion on uneven terrains. The sensory system consists of encoders for position feedback while the actuation system comprises of six precise DC motors. To enhance the learning outcomes of students and to permit readily realizaion of applications, developed software library supports three different command levels. The efficacy of the framework has been demonstrated by presenting a list of projects conducted on the framework. In particular, as a case-study, a project titled tether tracking and control of robotic rover has been detailed in the paper with presentation of experimental results. The pilot study indicated that incorporating the framework in robotics laboratory resulted in an efficient methodology of imparting interdisciplinary knowledge to engineering students. Additionally, the framework finds its potential in research of advanced robotic and control algorithms.
Khan A.A.,King Faisal University |
un Nabi S.R.,NED UET |
Iqbal J.,COMSATS Institute of Information Technology
Life Science Journal | Year: 2013
In mobile robotics, surface estimation and object recognition play vital role in navigation and control. This research presents a normal vector estimation method of a surface using Delaunay tessellation. The proposed strategy is an expansion of previously developed Continuous Nearest Neighbor Algorithm, underlining the trade-off between filtering and quality of input data. Initially, the 3D data points are segmented through a threshold process. The normal vectors are then determined based on an averaging method of centroids on Delaunay tessellation. Moreover, two similarity measures (vector angle and Euclidean distance) are considered for surface estimation of a pedestrian walk. Output from the Delaunay triangulation provides information for surface estimation. Results show that the proposed strategy has a great potential to be used for surface estimation in robotics.
Shahid M.,NED UET |
Saleem M.,Karachi Institute of Power Engineering |
Ibrahim F.,NED UET
Pakistan Journal of Scientific and Industrial Research Series A: Physical Sciences | Year: 2011
Activated carbon was produced from shisham wood and coconut shell through chemical activation, using phosphoric acid and low temperature carbonization. Proximate analysis and characterization ofthe product were carried out and Brunauer Emmett Teller (BET) surface area, total ash content, moisture content, pH value and iodine number were determined. The product characteristics were well comparable with those ofthe commercially available activated carbon.
Khatoon H.,NED UET |
Hafeez S.,Usman Institute of Technology |
Altaf M.T.,NED UET
Proceedings - 2011 9th International Conference on Frontiers of Information Technology, FIT 2011 | Year: 2011
Operating system plays a major role in effective memory management and has a significant impact on the performance of applications. In a Chip Multiprocessor, the onchip memory hierarchy is an important resource that plays a significant role in determining the overall performance of an application. In addition to a number of hardware optimization techniques that work for all types of applications, some software controlled optimization techniques are also effective for improving the performance of on-chip memory hierarchy. This is so because the software controlled techniques generally have a global view of other concurrently running workloads. A better solution to the memory performance problem is to couple the operating system policies and mechanisms to the hardware techniques for management of on-chip memory hierarchy and its optimizations. This paper gives an overview of all such designs that have coupled the on-chip cache optimization techniques with the operating system mechanisms and policies. More techniques are suggested that would be investigated to predict their effectiveness. © 2011 IEEE.