Themes

Salford hosts the Centre for Food Robotics and Automation, which undertakes advanced scientific research to develop all aspects of the food chain production process and to address the key needs of process automation and robotics within the food industry. The main objective of the research in this theme is to provide the food industry with fully functional, low cost and customized robotic and automation solutions, ranging from the development of flexible, multi-function grippers that can hygienically handle unpacked food products; specialised grippers are able to deal with special shaped foods as in our lasagne gripper; to the design of prototype machines for pet food production lines.

Several projects have also been undertaken in Aeronautical Engineering area, scoped either by Salford Academic Staff or by the aerospace industry such as Thales, Rolls Royce BAE systems, closely with Airbus UK, Brougton etc...

The projects have included:

• Investigate the feasibility of the "one way assembly" process and design a suitable clamping fixture, together with the appropriate manufacturing instructions.
• Joint relaxation and slave bolt design.
• Gap analysis on wing assemblies.
• Automation system for management of a natural gas tank.
• Temporary sealing of wing ribs for leak testing purposes.

Flexpicker

The group has extensive experience developing end effectors and grippers for grasping difficult to handle products. This project concerned the development of a gripper for the handling of delicate sliced fruit and vegetable products commonly found in the food industry. The device operates on the Bernoulli principle whereby air flow over the surface of an object generates a lift. The gripper allows objects to be lifted with minimal contact thereby reducing the chances of damaging or contaminating the object. The gripper was demonstrated with slices of tomato which are notoriously difficult to handle. A secondary benefit of the gripper is that it can also be used to remove surface moisture from the product produced during slicing. This drying effect is a feature particularly useful in some areas of food production. This system has been patented by the University.

Sprout Machine

This project considers automation in the preparation of Brussels sprouts as a value added food item. Within the processing of Brussels sprouts several tasks already have automated solutions but these require that the sprouts be fed to them in an exact and repeatable manner. To achieve this, feeding of the machines is performed manually. The work explored options for automating this product feed. A prototype machine was developed and tested using real products and was found to be capable of aligning 30 sprouts per minute in the desired orientation. This was achieved by exploiting the unique way in which a Brussels sprout rolls.

Assembly and Packaging of Triangular Sandwiches

The pre packed sandwich market is enormous but the production of sandwiches is very labour intensive. This project involved the design, construction and testing of an automated system for the assembly and packaging of triangular sandwiches. The work analysed the current manual production techniques and developed a number of modular workstations which could be incorporated into an existing line in place of human operators. The machine developed completes the final assembly of the sandwich and then cuts and packages it into a plastic skillet (container) for dispatch. To test the overall performance of the system real plant trials were conducted with the machine in a sandwich production factory.

Case Packing Machine

Traditional case packing machines tend to be expensive and often limited to a small range of products. Robots offer a much more flexible solution but these too tend to be an expensive and often low speed solution. This project developed a low cost gravity fed packing machine which could be adjusted to place both boxed or bagged products into cardboard cases.

The department has developed numerous other automated systems for the food industry on a commercial basis. This has involved working with the smallest of SMEs to large multinational companies.

The term "cognitive robotics" is used to refer to robots with higher level cognitive functions that involve knowledge representation and reasoning. Several projects are currently undertaken in this area in collaboration with psychologists and neuroscientist from European institutions such as IIT in Italy, Genoa and Ferrara.

Our research consist of endowing robots with some cognitive capabilities which are key elements to autonomous systems, such as perception processing, attention allocation, anticipation, planning, reasoning about other agents, and perhaps reasoning about their own mental states.

The term "cognitive robotics" is used to refer to robots with higher level cognitive functions that involve knowledge representation and reasoning. Several projects are currently undertaken in this area in collaboration with psychologists and neuroscientist from European institutions such as IIT in Italy, Genoa and Ferrara.

Examples of projects undertaken in the lab in this area are:

• Project carried out as a part of ASTRAEA T7 to develop a mechanism to present test cases to the ASTREA vehicle model for the handling of fuel system failure events within an open architecture. This project was critical for the whole internal integration of the ASTRAEA T7.
• Irrational Swarm: this project consists of endowing each agent/robots within the swarm with some irrational behaviour in order to mimic the human decision. The developed technique uses some psychological principles to model how the perceptions of human beings influence their choices from the given options.
• Probabilistic fuzzy reinforcement learning in social collaborative learning. This undergoing project is to use a hybrid algorithm and self-organizing particle system, enabling several robotic agents to learn an optimum behaviour combining their acquired knowledge about the environment to accomplish a given task, while dealing with the dimensionality problem of a real world environment, and its inherent uncertainties.
• Language grounding using the humanoid robot iCub platform. The main focus of this project is the investigation of the relationship between language and action.

Our centre has actively participated in the development of the state-of-the-art European cognitive platform "humanoid robot" RobotCUB (www.RobotCUB.org). The "iCub" is a child-like crawling robot that resembles a two-and-a-half-year-old child. The ultimate goal of this project is provide the cognition research community with an open human-like platform for the understanding of cognitive systems through the study of cognitive development. This work is supported by the European Commission FP6, Project IST-004370 and led by Professor Darwin Caldwell. The centre has developed the mechanics, electronics and control of the spine and legs of the iCub. The complete development leaded to numerous publications, in the mechanics as well as in control systems topics.

Additionally, our Centre is equipped with NAO humanoid robots (Aldebaran Robotics) for research and development of a wide range of algorithms, ranging from modelling Cognitive functions of cognitive robotics to walking algorithms and visual signal processing.

Gorilla

Traditional robot design has been concerned primarily with the development of structures and mechanisms that have high accuracy and speed but at the expense of high mass and power requirements and limited human interaction. Recent advances in computational power however have allowed lightweight and highly flexible structures, similar to those found in biological creations, to be used in robot design. This has led to the development of bio-mimetics were the trend is to try to emulate the 'soft' compliant structure of muscle, bone, tendons and skin and combine this with the power, robustness, accuracy, and endurance of mechanical drives. This work used pneumatic Muscle Actuators (pMAs) as a soft actuators that can macroscopically replicate much of the action of natural muscle. The actuators were tested in antagonistic pairs and used to power a robot primate (dimensionally comparable with a female gorilla) with a mass of less than 25kg constructed using light flexible materials.

Humanoid Robotic Hand

The University has a long history in the development of humanoid robotic hands. This particular hand was constructed for and installed at Manchester's Museum of Science and Industry. The vast majority of dextrous robot hands are used in laboratory environments and so long term reliability is rarely a major design consideration. However, reliability is critically important for a museum exhibit as it is not acceptable to have a display out of order for long periods of time. The hand designed in this work therefore had to be very reliable. The hand has a total of 15 degrees of freedom and was mounted to a 2 degree of freedom arm. An interface was produced allowing visitors to the museum to interact with the robot. This allowed them to use the robot to manipulate a ball and play simple tunes on a piano keyboard.

This field deals with the design and development of "human friendly" lower and upper body exoskeletons for walking gait assistance, arm rehabilitation for stroke patients and generic human force augmentation. Many of these wearable devices make use of braided pneumatic Muscle Actuators (pMAs): a new, low mass, high power to weight and volume actuation system.

Our Centre has been leading the research of novel control systems and development of enhanced versions of these actuators for the last decade. The advantage of the pMAs lies in how they produce a muscle-like contact, taking advantage of its inherent nature which weakens linearly as it contracts and as such can be considered a soft and bio mimetic actuation system. This capacity to "replicate" the function of natural muscle and inherent safety is extremely important when working in close proximity to humans, particularly those suffering a disability.

Salford University has been leading the research in haptics interfaces in UK for the last decade. Work has concentrated on the design and realisation of haptic interfaces, and in particular on the design of hand and arm exoskeletons for kinaesthetic feedback and finger tactile displays for object surface exploration (tactile feedback). Some of these projects have also been used for rehabilitation and training of medical personnel.

Another project deals with the development of interactive, affordable, easy to learn, risk-free, and reusable Medical training devices like our Cataract Eye Surgery Simulator (CESS). This can be used as a teaching and training method to train medical students adequately so that they can learn and master the skills required to perform surgery on live patients.

This research theme is concerned with the building of an Intelligent Collaborative Behavior using Multi-Agent Systems/robots using a novel swarm intelligent techniques. We have introduced the irrationality theory for the first time to swarm optimisation techniques and to swarm robotics. This concept was applied in wide range of applications such as path planning, obstacle avoidance and emergent behaviours, using state of the art Khepera robots (K-Team) for testing our algorithms as well as the widely used simulation software Webots (Cyberbotics) for simulating and testing our designed robot models. This work has been supported by the Eu-Cognition Network 2008.

Example of projects:

• Study and implementation of particle-based simulation algorithms, which can be used for simulating viscoelastic behaviours for particles systems. These implementations could be reused in several types of particles behaviour simulations; thereby the solution itself could be tuned specifically for a certain type of system or very easily adapted for others.
• Crowd behaviour modelling.
• Space and security robotics: space repair & assembly, planet exploration, environmental surveillance & monitoring, costal & sea patrol, fire & bomb fighting, surveillance of critical infrastructure, search rescue missions.
• Swarm agents for CCTV Monitoring: Collaborate between CCTV's in order to make the monitoring effective (with Meyertech Ltd).
• Swarm cognitive agents for autonomous computing over the network.
• Activity Level Monitoring System.
• Capture illegal processes (Games, chat, multi-media application etc).- Internet Monitoring.
• Application Management.
• Install /Uninstall applications on remote machines autonomously & silently.

An uninhabited autonomous system (UAS) must cope with unscripted procedures when conducting a mission where commands are issued at high levels of abstraction. It has to be designed around human-centric needs with the ability to perform tasks in accordance with instructions which lack adequate 'terms of reference'. These instructions can vary according to the needs of the mission such as 'search this area', 'report all detected anomalies' and 'find suitable targets'. Many aspects of the common and necessary but difficult operational issues need to be 'handed over' to automated procedures, thereby reducing the risk of failures. More Uninhabited Air Vehicles (UAVs) have been lost to landing accidents than in-flight technical failures and enemy action put together.

Since UAVs have led the development of UAS systems, they form ideal cases to illustrate the concepts. One of the key features of a relatively low cost aerodynamic based UAV system centres around the capability to deploy and re-acquire the vehicle without the need for a long runway. Hence this type of UAV tends to be ramp launched and parachute recovered. The control architecture is bespoked around a user's requirements rather than being aimed at the majority of likely customers. This significantly de-skills the control task and provides an intuitive interface for use by the operator groups such as military commanders.

The need to establish a strong partnership and team working between the autonomous systems and the humans-in-the-loop must be emphasised no matter how deep the degree of autonomy is. Each stage of the development must be accompanied by detailed risk analysis and the ability to recover from system failures. Since the vast majority of mission will be conducted beyond the line of sight (BLOS), the importance of 'cockpit control' requiring human authorisation for weapon release during lethal missions is of the essence, especially when the system is being deliberately jammed by hostile forces.

Knowledge is needed for reasoning and to make decisions but autonomy does not necessarily need artificial intelligence (AI). The barriers associated with operational realism are highly complex; sensor fit and their performance, tactical behavioural, legality & safety doctrine, safety and/or mission criticality issues and changing mission requirements needing a high level of flexibility.