The adoption of robotics is promising to improve the efficiency, quality, and safety of prefabricated construction. Besides technologies that improve the capability of a single robot, the automated assembly planning for robots at construction sites is vital for further improving the efficiency and promoting robots into practices. However, considering the highly dynamic and uncertain nature of a construction environment, and the varied scenarios in different construction sites, it is always challenging to make appropriate and up-to-date assembly plans. Therefore, this paper proposes a Deep Reinforcement Learning (DRL) based method for automated assembly planning in robot-based prefabricated construction. Specifically, a re-configurable simulator for assembly planning is developed based on a Building Information Model (BIM) and an open game engine, which could support the training and testing of various optimization methods. Furthermore, the assembly planning problem is modelled as a Markov Decision Process (MDP) and a set of DRL algorithms are developed and trained using the simulator. Finally, experimental case studies in four typical scenarios are conducted, and the performance of our proposed methods have been verified, which can also serve as benchmarks for future research works within the community of automated construction. Note to Practitioners —This paper is conducted based on the comprehensive analysis of real-life assembly planning processes in prefabricated construction, and the methods proposed could bring many benefits to practitioners. Firstly, the proposed simulator could be easily re-configured to simulate diverse scenarios, which can be used to evaluate and verify the operations’ optimization methods and new construction technologies. Secondly, the proposed DRL-based optimization methods can be directly adopted in various robot-based construction scenarios, and can also be tailored to support the assembly planning in traditional human-based or human-robot construction environments. Thirdly, the proposed DRL methods and their performance in the four typical scenarios can serve as benchmarks for proposing new advanced construction technologies and optimization methods in assembly planning.

Background: Lateral flow immunoassays (LFIAs) are being used worldwide for COVID-19 mass testing and antibody prevalence studies. Relatively simple to use and low cost, these tests can be self-administered at home, but rely on subjective interpretation of a test line by eye, risking false positives and false negatives. Here, we report on the development of ALFA (Automated Lateral Flow Analysis) to improve reported sensitivity and specificity. Methods: Our computational pipeline uses machine learning, computer vision techniques and signal processing algorithms to analyse images of the Fortress LFIA SARS-CoV-2 antibody self-test, and subsequently classify results as invalid, IgG negative and IgG positive. A large image library of 595,339 participant-submitted test photographs was created as part of the REACT-2 community SARS-CoV-2 antibody prevalence study in England, UK. Alongside ALFA, we developed an analysis toolkit which could also detect device blood leakage issues. Results: Automated analysis showed substantial agreement with human experts (Cohen’s kappa 0.90–0.97) and performed consistently better than study participants, particularly for weak positive IgG results. Specificity (98.7–99.4%) and sensitivity (90.1–97.1%) were high compared with visual interpretation by human experts (ranges due to the varying prevalence of weak positive IgG tests in datasets). Conclusions: Given the potential for LFIAs to be used at scale in the COVID-19 response (for both antibody and antigen testing), even a small improvement in the accuracy of the algorithms could impact the lives of millions of people by reducing the risk of false-positive and false-negative result read-outs by members of the public. Our findings support the use of machine learning-enabled automated reading of at-home antibody lateral flow tests as a tool for improved accuracy for population-level community surveillance.

Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm, which samples good state–action pairs from the experience replay buffer, our agent leverages entire episodes with hindsight to aid self-imitation learning. A selection module is introduced to filter uninformative samples from each episode of the update. The proposed method overcomes the limitations of the standard self-imitation learning algorithm, a transitions-based method which performs poorly in handling continuous control environments with sparse rewards. From the experiments, episodic self-imitation learning is shown to perform better than baseline on-policy algorithms, achieving comparable performance to state-of-the-art off-policy algorithms in several simulated robot control tasks. The trajectory selection module is shown to prevent the agent learning undesirable hindsight experiences. With the capability of solving sparse reward problems in continuous control settings, episodic self-imitation learning has the potential to be applied to real-world problems that have continuous action spaces, such as robot guidance and manipulation.