Outputs (32)

Achieving goals using reward shaping and curriculum learning (2023)
Presentation / Conference Contribution

Real-time control for robotics is a popular research area in the reinforcement learning community. Through the use of techniques such as reward shaping, researchers have managed to train online agents across a multitude of domains. Despite these adva... Read More about Achieving goals using reward shaping and curriculum learning.

Roots and models (2023)
Journal Article

One of us comes from dance, the other from robotics, and you would be forgiven for thinking immediately about the YouTube films created by Boston Dynamics. But what connects us is our concern that human-ness is losing ground to machine-ness. To partl... Read More about Roots and models.

Arts and humanities shaping the AI future (2023)
Preprint / Working Paper

The organisation of this event was motivated by the view there should be more Arts and Humanities (A&H) perspectives, methods and approaches involved in shaping our future relationship with AI technology.

Our invitation was sent to the most diver... Read More about Arts and humanities shaping the AI future.

Saltwater-responsive bubble artificial muscles using superabsorbent polymers (2022)
Journal Article

Robots operating in changing underwater environments may be required to adapt to these varying conditions. In tidal estuaries, for example, where the degree of salinity cycles in step with the level of the water, a robot may need to adapt its behavio... Read More about Saltwater-responsive bubble artificial muscles using superabsorbent polymers.

Benchmarking robots in smart cities (2022)
Journal Article

In order for robots to become integrated into society, we need to be able to prove that robots do their jobs reliably. Robot benchmarking competitions in smart cities offer a glimpse into our future.

A new perspective on robot ethics through investigating human–robot interactions with older adults (2021)
Journal Article

This work explored the use of human–robot interaction research to investigate robot ethics. A longitudinal human–robot interaction study was conducted with self-reported healthy older adults to determine whether expression of artificial emotions by a... Read More about A new perspective on robot ethics through investigating human–robot interactions with older adults.

Technology and risk considerations in shaping future drone legislation (2021)
Journal Article

The global aviation industry has decades-old and highly successful legislation enforcing safety in conventional manned aerospace. This framework has been evolved gradually around a set of mature technologies with particular goals and implementations,... Read More about Technology and risk considerations in shaping future drone legislation.

Onshoring through automation; Perpetuating inequality? (2021)
Journal Article

Many analyses of the ethical, legal and societal impacts of robotics are focussed on Europe and the United States. In this article I discuss the impacts of robotics on developing nations in a connected world, and make the case that international equi... Read More about Onshoring through automation; Perpetuating inequality?.

Pulsed thermography digital motion stabilization for the unmanned vehicle inspection of solar farms and GFRP wind blades through UAVs and UGVs (2021)
Presentation / Conference Contribution

The quality control of structures and fuselages in both the wind-turbine and solar sectors is a fundamental part that allows a lifetime assessment of their elements, from its initial assembly to the recurring inspection cycles. Automating the active... Read More about Pulsed thermography digital motion stabilization for the unmanned vehicle inspection of solar farms and GFRP wind blades through UAVs and UGVs.

Twin delayed hierarchical actor-critic (2021)
Presentation / Conference Contribution

Hierarchical Reinforcement Learning (HRL) addresses the common problem in sparse rewards environments of having to manually craft a reward function. We present a modified version of the Hierarchical Actor-Critic (HAC) architecture called Twin Delayed... Read More about Twin delayed hierarchical actor-critic.