Sample projects developed by staff and students - Click on the picture to view

Robot Learning

This project focuses on the training of robots to learn new actions and to communicate about their action capabilities. A teacher robot (the agent on your left in the movie) first gives a visual demonstrator to the learner robot (agent on the right) on how to perform actions such as "close_left_elbow" or "raise_right_arm". It also teaches the learner how to name these actions. Subsequently, the learner is able to autonomously acquire new action capabilities (e.g. "grabbing") simply by listening to a linguistic instruction explaining that "grabbing consists of close_left_elbow and close_right_elbow". This instruction can be given by the teacher robot, or by a human instructor..........more information (this will take you to another website)

Brain - Computer Interface

This movie shows a demo of the latest results of the Brain-Computer Music Interface (BCMI) project currently being developed by Prof E R Miranda. The system uses electroencephalogram (EEG) information to steer generative rules in order to compose and perform music. It constantly monitors the EEG of the subject and activates generative rules associated with the activity of different frequency bands of the spectrum of the EEG signal. The system also measures the complexity of the EEG signal in order to modulate the tempo (beat) and dynamics (loudness) of the performance. Opportunities for developing a projects in the area of BCMI are offered to students of this master programme.

Robotic Music

This movie shows a robotic system implemented by Etienne Drouet for his MRes project. The systems involves interactive autonomous singing robots programmed with appropriate motor, auditory and cognitive skills can evolve a shared lexicon of short musical melodies from scratch, after a period of spontaneous creation, adjustment and memory reinforcement. Musical expectation is defined as a sensory-motor mechanism whereby the robots evolve vectors of motor control parameters to produce imitations of heard intonation patterns. The robots are equipped with a voice synthesiser, a hearing apparatus and a memory device.

 

Robot Football - UK Champions

At the University of Plymouth we are continually developing a robot football team that currently partakes in competitions governed by FIRA.(Federation of International Robot soccer Association). FIRA Cup competitions bring together skilled researchers and students from different disciplines to play the game of robot soccer. There are many categories involving different size robots, pitches, and various levels of robot autonomy, which compete in different soccer tournaments.
The University of Plymouth are UK Champions Since 1997.

 

PSQ Symphony No 1

The is a piece of electronic music composed by Prof E Miranda for the inauguration of the new Portland Square building at the University. The music uses cutting-edge audio processing technology to synthesise and manipulate sounds. It was inspired by the paradox of the origins of music, as purported by philosopher Jean-Jacques Rousseau, who described the earliest spoken languages as being composed of vocal inflections such as warnings, cries for help, sho?ts, etc. In the beginning, these vocal utterances primarily expressed feelings, whilst gestures were preferred to express rational thought. As human society grew in complexity, spoken language needed to become more precise and less passionate. The composer intention was to...more

 

The Animator

Primarily the focus of this work is to investigate the adaptive nature of learning in a simulated robotic arm. We are interested in the learning that takes place when the objective of the robotic arm is touch a spherical or cube-shaped object. To investigate this learning we created a dataset of two simulated trials. Trial 1 - simulated the learning when the objective of the robotic arm is to touch a spherical object. Trial 2 -simulated whilst the arm was aiming to avoid a cube-shaped object. Each of these trials produced a dataset of 16 variables (the vertical axes in the parallel coordinate display). Each of these variables was simulated over a period of 150 time slices. We are interested in the variables involved in the behaviour of the robotic arm.

 

Information Visualization

Information Visualization aims to represent large quantities of data in novel ways. The data used in this movie is multi-dimensional spike train data. This movie is the animation of the activity of 10 neurons modelled as the movement of 10 particles in a 10 dimensional space. Thus, each particle has a location which is a 10 dimensional point. Can you picture that! Well that?s what we have done! Just like we use x, y and z for 3-d points. Here we are seeing 10-dimensional space in 2d. Each vertical axis represents one of the dimensions. The animation shows the movement of the particles (which is the activity of the neurons) over time. For more information read the journal paper.

 

The Tunnel

The Tunnel is a cylindrical investigation environment that supports user interaction. The snapshot shows the Tunnel visualization of a randomly generated multi-dimensional spike train dataset over 200ms. Each of the numbered horizontal bands encodes the spike train of the corresponding neuron. The two ?end? bands, band 1 and band 10 are adjacent to each other, thus forming the cylindrical environment. Time is represented down through the Tunnel. Overall, illumination inside the environment represents the firing of neurons in the currently displayed portion of the dataset. Synchrony is detected by perception of the position, intensity and frequency of light sources at different parts of the Tunnel. For more information please refer to the journal paper.

 

An Autonomous Wheelchair at an Art Gallery

An autonomous wheelchair has become a piece of art named "Psalms" in the exhibition entitled "Nine Night in Eldorado" by Donald Rodney, held at the South London Gallery until the 12th October 1997.

http://www.tech.plym.ac.uk/soc/staff/guidbugm/wheelchair/wheelc.htm

Instruction-Based learning for Mobile Robots

This project explores the acquisition of knowledge by intelligent Systems from Natural Language (NL) instruction. This is very effective in human learning and will be essential for adapting future intelligent systems to the needs of naive users. The aim of the project is to investigate real-world Instruction Based-Learning (IBL) in a generic route instruction task. Users can engage in a dialogue with a mobile robot equipped with artificial vision, in order to teach it how to navigate a simplified maze-like environment. The research focuses on the problem of how NL instructions can be used by an intelligent embodied agent to build a hierarchy of complex functions based on a limited set of low-level perceptual, motor and cognitive functions. Given the use of artificial vision and voice input, such a system can contribute to assisting visually impaired people and wheelchair users.

http://www.tech.plym.ac.uk/soc/staff/guidbugm/ibl/index.html