-
UKAEA-RACE-CP(26)032024
The primary objective of this work is to research, design, and draft an open standard for nuclear robotics, aiming to standardise the design, development, integration, interoperability, and overall through life capability management of technologies, devices, and platforms for robotic systems used in nuclear fusion and decommissioning operations.…
-
UKAEA-RACE-CP(25)012024
It is challenging to find optimum kinematic designs for non-standard robotic manipulators, e.g., medical, nuclear, and space manipulators, which are demanded to adapt to arbitrary complex tasks in constraints. Such design optimization can be modelled as a multi-dimensional non-convex optimization problem with nonlinear constrained conditions. Howev…
-
UKAEA-CCFE-PR(25)3172024
Polymers offer a number of properties of interest in robotics design, from the well established such as low weight, electrical and thermal insulation, to the more novel, where their visco-elasticity is of great benefit in designing vine robots and flexible sensors. The more dangerous the environment, for example in cases where high radiation is pre…
-
2024
This paper presents a detailed user study aimed at experimentally comparing the experience levels within bilateral teleoperation. The primary objective is to elucidate the key performance metrics that can effectively evaluate the competency level of human operators. Existing methodologies typically focus on the quantitative psychological evaluatio…
-
UKAEA-RACE-PR(25)032024
When using deep reinforcement learning (DRL) to perform multi-robot exploration in unknown environments, the training model may produce actions that lead to unpredictable system behaviours due to the complexity and unpredictability of the surroundings. Therefore, ensuring safe exploration with DRL becomes critical. To tackle this issue, we propo…
-
UKAEA-RACE-PR(25)022024
Finding optimum kinematic designs for non-standard robotic manipulators, such as those used in medical, nuclear, and space applications is challenging due to the need to adapt to complex tasks within constrained environments. This design optimization problem is multi-dimensional and non-convex, with nonlinear constraints. Ensuring reachability, …
-
UKAEA-RACE-CP(26)022023
When using mobile robots to perform data collection about the surroundings, the performance might be dissatisfying since the environments could be unknown and challenging. This situation will pose challenges for mobile robot navigation and exploration. To tackle this issue, we propose a consensus-based deep reinforcement learning (DRL) algorithm…
-
UKAEA-CCFE-PR(23)1852023
Piping systems that transport coolant and breeding fluid are naturally an essential part of the support system of the nuclear fusion power plants. Following a campaign of operations, the reactor is required to be shut down and maintained entirely. Pipes connected to the reactor components are to be cut, re-welded or re-joined, and inspected non-des…
-
UKAEA-RACE-CP(23)122023
Fukushima Daiichi decommissioning is a long-term engineering challenge, of which advanced control techniques are essentially demanded. In the past ten years, the success in various decommissioning operations demonstrates the importance of elaborating state-of-the-art control and automation technologies. However, there are still various control engi…
-
UKAEA-RACE-CP(23)092023
When transferring a Deep Reinforcement Learning (DRL) model from simulation to the real world, the performance could be unsatisfactory since the simulation cannot imitate the real world well in many circumstances. This results in a long period of fine-tuning in the real world. This paper proposes a self-supervised vision-based DRL method that al…
Showing 11 - 20 of 39 UKAEA Paper Results