Enabling Technologies for Autonomous Robotic Systems in Manufacturing

Research of autonomous manufacturing systems is motivated both by the new technical possibilities of cyber-physical systems and by the practical needs of the industry.Autonomous operation in semi-structured industrial environments can now be supported by advanced sensor technologies,digital twins,artificial intelligence and novel communication techniques.These enable real-time monitoring of production processes,situation recognition and prediction,automated and adaptive(re)planning,teamwork and performance improvement by learning.This paper summarizes the main requirements towards autonomous industrial robotics and suggests a generic workflow for realizing such systems.Application case studies will be presented from recent practice at HUN-REN SZTAKI in a broad range of domains such as assembly,welding,grinding,picking and placing,and machining.The various solutions have in common that they use a generic digital twin concept as their core.After making general recommendations for realizing autonomous robotic solutions in the industry,open issues for future research will be discussed.

Curve Trajectory Model for Human Preferred Path Planning of Automated Vehicles

Automated driving systems are often used for lane keeping tasks.By these systems,a local path is planned ahead of the vehicle.However,these paths are often found unnatural by human drivers.In response to this,this paper proposes a linear driver model,which can calculate node points reflective of human driver preferences and based on these node points a human driver preferred motion path can be designed for autonomous driving.The model input is the road curvature,effectively harnessed through a self-developed Euler-curve-based curve fitting algorithm.A comprehensive case study is undertaken to empirically validate the efficacy of the proposed model,demonstrating its capacity to emulate the average behavioral pat-terns observed in human curve path selection.Statistical analyses further underscore the model's robustness,affirming the authenticity of the established relationships.This paradigm shift in trajectory planning holds promising implications for the seamless integration of autonomous driving systems with human driving preferences.

DeepFilter: A Deep Learning Based Variant Filter for VarDict

With the development of sequencing technologies,somatic mutation analysis has become an important component in cancer research and treatment.VarDict is a commonly used somatic variant caller for this task.Although the heuristic-based VarDict algorithm exhibits high sensitivity and versatility,it may detect higher amounts of false positive variants than callers,limiting its clinical practicality.To address this problem,we propose DeepFilter,a deep-learning based filter for VarDict,which can filter out the false positive variants detected by VarDict effectively.Our approach trains two models for insertion-deletion mutations(InDels)and single nucleotide variants(SNVs),respectively.Experiments show that DeepFilter can filter at least 98.5%of false positive variants and retain 93.5%of true positive variants for InDels and SNVs in the commonly used tumor-normal paired mode.Source code and pre-trained models are available at https://github.com/LeiHaoa/DeepFilter.

Machine Learning Techniques for Predicting Crop Photosynthetic Capacity from Leaf Reflectance Spectra

Harnessing natural variation in photosynthetic capacity is a promising route toward yield increases, but physiological phenotyping is still too laborious for large-scale genetic screens. Here, we evaluate the potential of leaf reflectance spectroscopy to predict parameters of photosynthetic capacity in Brassica oleracea and Zea mays, a C3 and a C4 crop, respectively. To this end, we systematically evaluated properties of reflectance spectra and found that they are surprisingly similar over a wide range of species. We assessed the performance of a wide range of machine learning methods and selected recursive feature elimination on untransformed spectra followed by partial least squares regression as the preferred algorithm that yielded the highest predictive power. Learning curves of this algorithm suggest optimal species-specific sample sizes. Using the Brassica relative Moricandia, we evaluated the model transferability between spe- cies and found that cross-species performance cannot be predicted from phylogenetic proximity. The final intra-species models predict crop photosynthetic capacity with high accuracy. Based on the estimated model accuracy, we simulated the use of the models in selective breeding experiments, and showed that high-throughput photosynthetic phenotyping using our method has the potential to greatly improve breeding success. Our results indicate that leaf reflectance phenotyping is an efficient method for improving crop photosynthetic capacity.

Selection for Cheaper Amino Acids Drives Nucleotide Usage at the Start of Translation in Eukaryotic Genes

Coding regions have complex interactions among multiple selective forces,which are manifested as biases in nucleotide composition.Previous studies have revealed a decreasing GC gradient from the 5′-end to 3′-end of coding regions in various organisms.We confirmed that this gradient is universal in eukaryotic genes,but the decrease only starts from the~25th codon.This trend is mostly found in nonsynonymous(ns)sites at which the GC gradient is universal across the eukaryotic genome.Increased GC contents at ns sites result in cheaper amino acids,indicating a universal selection for energy efficiency toward the N-termini of encoded proteins.Within a genome,the decreasing GC gradient is intensified from lowly to highly expressed genes(more and more protein products),further supporting this hypothesis.This reveals a conserved selective constraint for cheaper amino acids at the translation start that drives the increased GC contents at ns sites.Elevated GC contents can facilitate transcription but result in a more stable local secondary structure around the start codon and subsequently impede translation initiation.Conversely,the GC gradients at four-fold and two-fold synonymous sites vary across species.They could decrease or increase,suggesting different constraints acting at the GC contents of different codon sites in different species.This study reveals that the overall GC contents at the translation start are consequences of complex interactions among several major biological processes that shape the nucleotide sequences,especially efficient energy usage.

On the relationship between the activity at point of interests and road traffic

The estimation and analysis of road traffic represent the preliminary steps towards satisfying the current needs for smooth,safe,and green transportation.Therefore,effective traffic monitoring is an essential topic alongside the planning of sustainable transportation systems and the development of new traffic management concepts.In contrast to classical traffic detection solutions,this study investigates the correlation between travelers'social activities and road traffic.The s's primary goal is to investigate the presence of the relationship between social activity and road traffic,which might allow an infrastructure-independent traffic monitoring technique as well.People's general activities at Point of Interest(POI)locations(measured as occupancy parameter)are correlated with traffic data so that,finally,proper proxys can be defined for link-level average traffic speed estimation.The method is tested and evaluated using real-world traffic and POI occupancy data from Budapest(District XI.).The results of the correlation investigation justify an indirect relationship between activity at POIs and road traffic,which holds promise for future practical applicability.

Bilevel programming approach to demand response management with day-ahead tariff

This paper introduces a bilevel programming approach to electricity tariff optimization for the purpose of demand response management(DRM)in smart grids.In the multi-follower Stackelberg game model,the leader is the profit-maximizing electricity retailer,who must set a time-of-use variable energy tariff in the grid.Followers correspond to the groups of prosumers(simultaneous producers and consumers of the electricity).They respond to the observed tariff,schedule controllable loads and determine the charging/discharging policy of their batteries to minimize the cost of electricity and to maximize the utility at the same time.A bilevel programming formulation of the problem is defined,and its fundamental properties are proved.The primal-dual reformulation is proposed in this paper to convert the bilevel optimization problem into a single-level quadratically constrained quadratic program(QCQP),and a successive linear programming(SLP)algorithm is applied to solve it.It is demonstrated in computational experiments that the proposed approach outperforms earlier typical methods based on the KarushKuhn-Tucker(KKT)reformulation regarding both solution quality and computational efficiency on practically relevant problem sizes.Besides,it also offers more flexible modeling capabilities.

Online Induction of Probabilistic Real-Time Automata

The probabilistic real-time automaton （PRTA） is a representation of dynamic processes arising in the sciences and industry. Currently, the induction of automata is divided into two steps： the creation of the prefix tree acceptor （PTA） and the merge procedure based on clustering of the states. These two steps can be very time intensive when a PRTA is to be induced for massive or even unbounded datasets. The latter one can be efficiently processed, as there exist scalable online clustering algorithms. However, the creation of the PTA still can be very time consuming. To overcome this problem, we propose a genuine online PRTA induction approach that incorporates new instances by first collapsing them and then using a maximum frequent pattern based clustering. The approach is tested against a predefined synthetic automaton and real world datasets, for which the approach is scalable and stable. Moreover, we present a broad evaluation on a real world disease group dataset that shows the applicability of such a model to the analysis of medical processes.