In an immersive computationally intelligent virtual reality (VR) environment, humans can interact with a virtual 3D scene and navigate a robotic device. The non-destructive nature of VR makes it an ideal testbed for many applications and a prime candidate for use in rehabilitation robotics simulation and patient training. We have developed a testbed for robot mediated neurorehabilitation therapy that combines the use of robotics, computationally intelligent virtual reality and haptic interfaces. We have employed the theories of neuroscience and rehabilitation to develop methods for the treatment of neurological injuries such as stroke, spinal cord injury, and traumatic brain injury. As a sensor input we have used two stateof-the-art technologies, depicting the two different approaches to solve the mobility loss problem. In our first experiment we have used a 52 piezoresistive sensor laden shirt as an input device to capture the residual signals arising from the patient's body. In our second experiment, we have used a precision position tracking (PPT) system to capture the same signals from the patient's upper body movement. The key challenge in both of these experiments was to accurately localise the movement of the object in reality and map its corresponding position in 3D VR. In this book chapter, we describe the basic theory of the development phase and of the operation of the complete system. We also present some preliminary results obtained from subjects using upper body postures to control the simulated wheelchair.