-
UKAEA-RACE-PR(23)072023
This paper reports on the analysis of potential rail-based maintenance systems when implemented into a Helical Advanced Stellarator (HELIAS) 5-B device. The main purpose of such a system would be to handle and exchange the internal vessel components, namely the breeding blanket segments, which are expected to be the largest and heaviest componen…
-
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…
-
UKAEA-RACE-CP(23)082023
Many complex domains would benefit from the services of Large-scale, Safety-verified, Always-on (LSA) robotic systems. However, existing large-scale solutions often forego the complex reasoning required for safety verification and prescient reasoning in favour of scalability. We propose a method of partitioning the task domain to enable scalabil…
-
UKAEA-RACE-CP(23)072023
We consider planning problems where a robot must visit a large set of locations to complete a task at each one. Our focus is problems where the difficulty of each task, and thus its duration, can be predicted, but not fully known in advance. We propose a general Markov decision process (MDP) model for difficulty-aware problems, and propose varia…
-
UKAEA-RACE-CP(23)062023
Sim-and-real training is a promising alternative to sim-to-real training for robot manipulations. However, the current sim-and-real training is neither efficient, i.e., slow convergence to the optimal policy, nor effective, i.e., sizeable real-world robot data. Given limited time and hardware budgets, the performance of sim-and-real training is …
-
UKAEA-RACE-PR(23)052023
ITER In-Vessel Components (IVCs) will have limited lifetimes and need to be maintained and/or replaced during the operational life of ITER. IVCs are attached to the plant cooling water system via pipework to enable active cooling of the components during plasma operations. When maintenance is required, Remote Handling Systems (RHS) will be used …
-
UKAEA-RACE-CP(23)052023
Wireless Sensor Networks (WSN) have been shown to improve data gathering processes over large spacial and temporal scales at a low cost [1], as well as the automation of decision making processes in complex industrial settings [2]. The nuclear sector is no exception to this, being obvious applications structural health monitoring [3] and radiation…
-
UKAEA-RACE-PR(23)032022
Calibration data for condition monitoring (CM), often originates from equipment running in different environment conditions, and operational settings. Due to the uneven distribution of the data, the performance of traditional machine learning approaches for CM can easily be skewed in favour of operating conditions with larger data distributions.…
-
UKAEA-RACE-CP(23)022021
Robotic systems that enable the operators to remotely manipulate delicate materials with high dexterity and sufficient force feedback will pave the path for improvements of the safe maintenance and decommissioning processes within the nuclear industry. Training the operators, however, for challenging conditions (e.g., low visibility, restricted …
-
UKAEA-RACE-CP(23)032021
This paper reports on a study of the existing or proposed maintenance arm systems with similar functions and structure to that of the proposed DEMO Multi-Purpose Deployer (MPD).The current MPD design iteration consists of a boom deployment system that is ~30m long and can support a payload of ~1000kg, while still being able to access the DEMO va…
Showing 21 - 30 of 75 UKAEA Paper Results