Using Computational Intelligence for Improved Teleoperation over Wireless Network

Using Computational Intelligence for Improved Teleoperation over Wireless Network

Salman H. Khan (National University of Sciences & Technology (NUST), Pakistan), Arsalan H. Khan (Northwestern Polytechnical University (NPU), P.R. China) and Zeashan H. Khan (Center for Emerging Sciences, Engineering and Technology (CESET), Pakistan)
DOI: 10.4018/978-1-4666-1830-5.ch007
OnDemand PDF Download:
No Current Special Offers


The role of computational intelligence techniques in applied sciences and engineering is becoming popular today. It is essential because the autonomous engineering applications require intelligent decision in real time in order to achieve the desired goal. This chapter discusses some of the approaches to demonstrate various applications of computational intelligence in dependable networked control systems and a case study of teleoperation over wireless network. The results have shown that computational intelligence algorithms can be successfully implemented on an embedded application to offer an improved online performance. The different approaches have been compared and could be chosen as per application requirements.
Chapter Preview


Computational intelligence (CI) has its roots in close observation of the natural phenomenon and it combines a set of fuzzy, adaptive and evolutionary methods that are intelligent enough to learn from experience to effectively solve problems. CI is enabling new ways to develop intelligent systems that will one-day outclass humans in self learning, model development and prediction. The earlier methods of artificial intelligence, AI (or, GOFAI i.e., Good Old-Fashioned Artificial Intelligence, as per the term introduced by John Haugeland, professor of philosophy at the University of Chicago) were logic based approaches that have evolution from top to bottom (Guturu, 2008). In contrast, the modern CI methods generally have bottom-to-top where model is built from unstructured beginning. They use stochastic or heuristic optimization algorithms and strategies such as Fuzzy Systems, Neural Networks, Evolutionary Computation, Rough sets, Hybrid methods, Swarm Intelligence, Symbolic Machine learning, Statistical data mining, Artificial Immune Systems, etc.

Teleoperation includes Monitoring, Supervision, Control, Diagnosis and it deals with the interaction between Network/Communication and Control. It may be considered as a special case of network controlled systems (NCS) with specific terminology of master and slave subsystems sharing control information over a communication network. The network controlled systems (NCS) are those systems where at least one of the subsystem i.e. sensor, actuator and controller communicate over a network (Khan et al, 2010). For NCS, the quality of service (QoS) of the network is of utmost importance which is defined as the capability to differentiate between different traffic classes (or users) as compared to other traffic (or users) (Park, 2005). It also takes into account the parameters of data link e.g. signal to noise ratio (SNR), bit error rate (BER) and packet loss rate (PLR), jitter, and network utilization (throughput), which gives a measure of successful delivery of data packets. Some of the parameters of network QoS are shared with the objective QoS. Quality of control (QoC) in NCS is referred to as the desired performance delivered by the closed-loop control system (robot in our case). Various parameters of QoC include stability, response time, steady-state performance, etc. among which stability is of premier importance in QoC analysis (Mechraoui et al, 2009).

The network based teleoperation is known to be of several types. This includes unilateral teleoperation where the control information/command moves unidirectional as can be seen in Figure 1. The other possibility is to exchange some data between the master/slave stations as is the case of bilateral teleoperation. This may be a visual feedback via camera to assist operator at the master station as in Figure 2.

Figure 1.

Unilateral teleoperation

Figure 2.

Bilateral teleoperation


In the third type, force feedback is provided to the operator so that he can feel the environment. The force feedback is usually coupled with visual information as seen in Figure 3 below.

Figure 3.

Bilateral teleoperation with force feedback


Complete Chapter List

Search this Book: