Heriot-Watt University

University: 
Heriot-Watt University

Fabrication of Soft Robotic Electronic Skin (E-Skin)

Project number: 
120020
To design and develop stretchable e-skin for wearable and soft robotic applications, utilising novel digital manufacturing process.
Dr. Morteza Amjadi
Heriot-Watt University

Soft e-skins have recently attracted considerable research interest due to their applications in soft robotics, prosthetics, and artificial skins. Remarkable advances in materials science, nanotechnology, and biotechnology have led to the development of various e-skins capable of detecting different external stimuli, such as strain, pressure, temperature, hydration, and biomarkers.

University: 
Heriot-Watt University
University: 
Heriot-Watt University

Robots Safe and Secure by Construction

Project number: 
400007
Verified implementation of machine-learning components of autonomous systems
Prof. Ekaterina Komendantskaya
Heriot-Watt University

Robotic applications spread to a variety of application domains, from autonomous cars and drones to domestic robots and  personal devices. Each application domain comes with a rich set of requirements such as legal policies, safety and security standards, company values, or simply public perception. They must be realised as verifiable properties of software and hardware. Consider the following policy: a self-driving car must never break the highway code.

Deep Analysis: A Critical Enabler to Certifying Robotic and Autonomous Systems

Project number: 
300007
Develop techniques that assist in certifying robotic and autonomous systems through a deep analysis at the level of requirements, problem worlds and specifications.
Prof. Andrew Ireland
Heriot-Watt University

Safety critical robotic and autonomous systems, such as Unmanned Air Vehicles (UAVs) that operate beyond visual line of sight, require the highest level of certification. Certifiers are concerned with how such systems behave within their environment – as defined by system wide requirements, e.g. compliance with the rules-of-the-air (i.e. SERA).   In contrast, software developer’s focus on specifications - how the system software should behave based upon operational modes and input signals. Many catastrophic system failures, e.g.

Multimodal fusion for large-scale 3D mapping

Project number: 
134001
The project will explore the combination of 3D point clouds with imaging modalities (colour, hyperspectral images) via machine learning and computer graphics to improve the characterization of complex 3D scenes.
Dr. Yoann Altmann
Heriot-Watt University

Lidar point clouds have been widely used to segment large 3D scenes such as urban areas and vegetated regions (forests, crops, …), and to build elevation profiles. However, efficient point cloud analysis in the presence of complex scenes and partially transparent objects (e.g, forest canopy) is still an unsolved challenge.

Wearable and Stretchable Stain/Tactile Sensors for Soft Robotic Applications

Project number: 
120018
To design and develop stretchable optomechanical sensors, and investigate their integration with soft gripper robots towards soft robots with feedback sensation
Dr. Morteza Amjadi
Heriot-Watt University

Wearable sensor technologies have recently attracted tremendous attention due to their potential applications in soft robotics, human motion detection, prosthetics, and personalized healthcare monitoring. Remarkable advances in materials science, nanotechnology, and biotechnology have led to the development of various wearable and stretchable sensors. For example, researchers including us have developed resistive and capacitive-type strain and pressure sensors and demonstrated their use in soft robotics, tactile sensing and perception, and human body motion detection.

University: 
Heriot-Watt University

Rethinking Deep Learning on Remote Smart Sensors

Project number: 
140027
Develop new neural network compression mechanisms to accelerate neural networks on low powered FPGA and embedded GPU smart sensors
Dr. Robert Stewart
Heriot-Watt University

Neural networks for deep learning have been proven successful for many different domains, such as autonomous driving, conversational agents, autonomous robotics and computer vision. Neural network models are typically trained and executed on GPUs, but these have significant energy costs and lack portability needed for remote smart devices. FPGAs and embedded GPUs solve this problem, but cannot host large trained models. Thus, mechanisms to compress neural networks are needed to fit within hardware resource constraints without losing accuracy of AI inferences the model can make.