Safety-aware Adversarial Inverse Reinforcement Learning (S-AIRL) for Highway Autonomous Driving

Inverse reinforcement learning (IRL) has been successfully applied in many robotics and autonomous driving studies without the need for hand-tuning a reward function. However, it suffers from safety issues. Compared to the reinforcement learning (RL) algorithms, IRL is even more vulnerable to unsafe situations as it can only infer the importance of safety based on expert demonstrations. In this paper, we propose a safety-aware adversarial inverse reinforcement learning algorithm (S-AIRL). First, the control barrier function (CBF) is used to guide the training of a safety critic, which leverages the knowledge of system dynamics in the sampling process without training an additional guiding policy. The trained safety critic is then integrated into the discriminator to help discern the generated data and expert demonstrations from the standpoint of safety. Finally, to further improve the safety awareness, a regulator is introduced in the loss function of the discriminator training to prevent the recovered reward function from assigning high rewards to the risky behaviors. We tested our S-AIRL in the highway autonomous driving scenario. Comparing to the original AIRL algorithm, with the same level of imitation learning (IL) performance, the proposed S-AIRL can reduce the collision rate by 32.6%.

Sequential Decisions from Sampling: Inductive Generation of Stopping Decisions Using Instance-Based Learning Theory

Sequential decisions from sampling are common in daily life: we often explore alternatives sequentially, decide when to stop such exploration process, and use the experience acquired during sampling to make a choice for what is expected to be the best option. In decisions from experience, theories of sampling and experiential choice are unable to explain the decision of when to stop the sequential exploration of alternatives. In this chapter, we propose a mechanism to inductively generate stopping decisions, and we demonstrate its plausibility in a large and diverse human data set of the binary choice sampling paradigm. Our proposed stopping mechanism relies on the choice process of a theory of experiential choice, Instance-Based Learning Theory (IBLT). The new stopping mechanism tracks the relative prediction errors of the two options during sampling, and stops when such difference is close to zero. Our results from simulation are able to accurately predict human stopping decisions distributions in the dataset. This model provides an integrated theoretical account of decisions from experience, where the stopping decisions are generated inductively from the sampling process.

Boosting serotonin increases information gathering by reducing subjective cognitive costs

Serotonin is implicated in the valuation of aversive costs, such as delay or physical effort. However, its role in governing sensitivity to cognitive effort, for example deliberation costs during information gathering, is unclear. We show that week-long treatment with a serotonergic antidepressant enhances a willingness to gather information when trying to maximize reward. Using computational modelling, we show this arises from a diminished sensitivity to subjective deliberation costs during the sampling process. This result is consistent with the notion that serotonin alleviates sensitivity to aversive costs in a domain-general fashion, with implications for its potential contribution to a positive impact on motivational deficits in psychiatric disorders.

Aerial and Optical Images-Based Plant Species Segmentation Using Enhancing Nested Downsampling Features

Plant species, structural combination, and spatial distribution in different regions should be adapted to local conditions, and the reasonable arrangement can bring the best ecological effect. Therefore, it is essential to understand the classification and distribution of plant species. This paper proposed an end-to-end network with Enhancing Nested Downsampling features (END-Net) to solve complex and challenging plant species segmentation tasks. There are two meaningful operations in the proposed network: (1) A compact and complete encoder–decoder structure nests in the down-sampling process; it makes each downsampling block obtain the equal feature size of input and output to get more in-depth plant species information. (2) The downsampling process of the encoder–decoder framework adopts a novel pixel-based enhance module. The enhanced module adaptively enhances each pixel’s features with the designed learnable variable map, which is as large as the corresponding feature map and has n×n variables; it can capture and enhance each pixel’s information flexibly effectively. In the experiments, our END-Net compared with eleven state-of-the-art semantic segmentation architectures on the self-collected dataset, it has the best PA (Pixel Accuracy) score and FWloU (Frequency Weighted Intersection over Union) accuracy and achieves 84.52% and 74.96%, respectively. END-Net is a lightweight model with excellent performance; it is practical in complex vegetation distribution with aerial and optical images. END-Net has the following merits: (1) The proposed enhancing module utilizes the learnable variable map to enhance features of each pixel adaptively. (2) We nest a tiny encoder–decoder module into the downsampling block to obtain the in-depth plant species features with the same scale in- and out-features. (3) We embed the enhancing module into the nested model to enhance and extract distinct plant species features. (4) We construct a specific plant dataset that collects the optical images-based plant picture captured by drone with sixteen species.

Simulation analysis and experiment of sampling process of wheel brush sampler based on discrete element method

In order to study the brush sweep sampling process through simulation analysis, the structure of the asteroid sampler is simplified on the basis of retaining the wheel brush. Soybean particles are selected as the verification sampling particles, and the physical and contact parameters of calibrated soybean particles are applied to the discrete element simulation software EDEM and the relationship between the sampling wheel brush speed and torque is analysed. At the same time, a set of wheel brush asteroid sampler ground torque test system is built to verify the accuracy of the discrete element simulation results. The results show that the driving torque of the sampling wheel brush is mutational in the process of sampling, and the faster the rotation speed of the sampling wheel brush, the more the mass of the collected particles, and the greater the driving torque required for the sampling wheel brush. This research provides a method basis for the structure selection and parameter optimization design of the asteroid sampler.

Explore Protein Conformational Space With Variational Autoencoder

Molecular dynamics (MD) simulations have been actively used in the study of protein structure and function. However, extensive sampling in the protein conformational space requires large computational resources and takes a prohibitive amount of time. In this study, we demonstrated that variational autoencoders (VAEs), a type of deep learning model, can be employed to explore the conformational space of a protein through MD simulations. VAEs are shown to be superior to autoencoders (AEs) through a benchmark study, with low deviation between the training and decoded conformations. Moreover, we show that the learned latent space in the VAE can be used to generate unsampled protein conformations. Additional simulations starting from these generated conformations accelerated the sampling process and explored hidden spaces in the conformational landscape.

Which routes for optimal yield sampling in viticulture?

Estimating vineyard crop yield is important for preparing harvesting operations and vatting. Estimations are generally carried out by sampling shortly before harvest and observations are made on a limited number of sampling sites. The sampling process has obvious practical constraints, such as the time allocated to the operation, which determines both the number of sites to be sampled and the route to reach them.

Evaluation of Iso 9001:2015 Risk Control in Case of Used Antigen Swab

The number of domestic passengers departing from the Medan Polonia airport was on average as many as hundreds of thousands of passengers per month. Where every passenger is required to carry out a covid antigen examination, one of which is an antigen swab examination. At the end of April 2021, the Police uncovered a case of using a used antigen test kit at Kualanamu Airport. Therefore, the author tries to evaluate and review the antigen swab process in Kualanamu Medan to take technical steps for risk-related assessments at the antigen swab sampling facility. This research design uses a literature study by studying theories and secondary data. Based on data obtained from the Statistics Agency as many as hundreds of thousands of people using domestic flights from Polonia airport. To reduce risk organizations make the existing process risks, namely, the sampling process, specimen examination, data analysis and supervision from the head office, where the probability risk greatly affects the organization. The five steps of improving diagnostic pharmaceutics are considered good in solving the problems at hand, but perhaps the additional implementation of improvements must be carried out more consistently and using risk base thinking and PDCA cycle.

VERIFIKASI METODE ANALISIS METAMFETAMINA DAN AMFETAMINA DALAM MATRIKS URIN SECARA AUTOMATISASI DENGAN GERSTEL® DISPOSABLE PIPETTE EXTRACTION (DPX) MULTIPURPOSE SAMPLER (MPS)

Method analytical validation and verification is crucial in routine qualitative and quantitative analysis. Analysis laboratory need objective evidences about specific parameters in their drugs/analytes or drugs metabolites in matrices biology. Urine is the most preferable matrix biology for determining drugs metabolites especially in drug abuses cases because urine’s sampling process is not invasive. There are many methods extracting drugs in urine, especially methamphetamine and amphetamine as those two analytes are excreted via urine. This study presented method verification for determination of methamphetamine and amphetamine in urine using Gerstel® automated Disposable Pipette Extraction (DPX) Multipurpose Sampler (MPS). Result of this study showed that retention time of methamphetamine is in minute 6.21, and amphetamine is in minute 3.15. Methampethamine’s curve displayed a coefficient of determination r2=0,9999 with the equation y=170,19x+33183. The equation of amphetamine showed y=44390x – 17513 with coefficient of determination r2= 0,9974. Limit of detection (LOD) of methamphetamine in urine is 59,73 ppb, and LOD of amphetamine is 36 ppb.

Mengovirus as Process Control Virus in the Monitoring of Genomic RNA and Infectivity of Enteric Viruses in Water Matrices

The present study, developed in the scope of a survey to monitor enteric viruses in natural surface water and drinking water sources, addressed the suitability of mengovirus to assess viral recovery rates at two steps of the water sampling process. In a pilot campaign comprising two samples from each type of water source, when mengovirus was added after the filtration/primary concentration step, the recovery rates of viral RNA were higher than 18% and identical for both water matrices. In a one-year sampling campaign, where mengovirus was present along the whole sample processing (addition in the filtration/primary concentration step), significantly different recovery rates were observed between water matrices: usually higher than 1% in drinking water and under 1% in surface water. The results suggest the first stage of the water sampling process and the type of water matrix are the most influential factors for viral RNA recovery. This study also addressed and evidenced mengovirus replication and titration in Vero E6 cultures and showed infectious mengovirus to be recovered from samples of both types of water matrix. These results anticipate a more comprehensive applicability of mengovirus as a process control virus in the monitoring of viruses in water, extended to viral infectivity.