Considerations of potential runaway motion and physical interaction for speed and separation monitoring

In the field of human-robot collaboration (HRC), the speed and separation monitoring (SSM) collaboration have attracted much attention owing to its non-contact safety strategy. 3D sensing applications are currently of interest for industrial automation technology and are considered to be a promising method for maximizing the efficiency of SSM. However, little attention has been given to the runaway space of the robot or the potential contact due to the foreseeable misuse of the operator. In this study, experiments are conducted using a radar system as an example of a 3D safety-related sensor, and battery assembly scenarios are carried out for the comparison. In the experiment, two different orientations of the robot are tested, considering the potential runaway motion of the robot. Also, the maximum permissible speed of the robot is calculated by geometrical transfer energy, which is based on effective mass and the velocity of the manipulator and human injury criteria. From the experimental results, it is evident that it is better to avoid placing the vertical articulated robot in front of the operator from the perspective of minimizing the effect of runaway motion into the safety distance. Finally, the proposed framework of speed limitation is thought to be an effective method to link SSM and power and force limiting safety function.     

Implementing speed and separation monitoring in collaborative robot workcells

We provide an overview and guidance for the speed and separation monitoring methodology as presented in the International Organization of Standardization's technical specification 15066 on collaborative robot safety. Such functionality is provided by external, intelligent observer systems integrated into a robotic workcell. The SSM minimum protective distance function equation is discussed in detail, with consideration for the input values, implementation specifications, and performance expectations. We provide analytical analyses and test results of the current equation, discuss considerations for implementing SSM in human-occupied environments, and provide directions for technological advancements toward standardization.     

兼具柔顺与安全的助行机器人运动控制研究

针对助行机器人的柔顺性和安全性问题,基于多传感器系统融合技术,本文提出了一种能够兼具柔顺与安全的助行机器人运动控制方法.首先介绍了助行机器人的机械结构、控制原理以及多传感器系统,然后根据机器人多传感器系统,设计出各传感器相对应的用户意图估计方法,提出了一种基于多传感器融合的助行机器人柔顺运动控制算法.分析用户可能发生的跌倒模式,使用基于卡尔曼滤波（Kalman filter,KF）的序贯概率比检验（Sequential probability ratio test,SPRT）方法和决策函数来判断用户是否会跌倒,并判断处于哪种跌倒模式.最后,通过助行机器人柔顺运动控制实验和用户跌倒检测实验验证了算法的有效性.     

Brain signal-based safety measure activation for robotic systems

In this paper, we present our approach for using EEG signals to activate safety measures of a robot when an error or unexpected event is perceived by the human operator. In particular, we consider brain-based error perception while the operator passively observes the robot performing an action. Our approach consists of monitoring EEG signals and detecting a brain potential called error related negativity (ERN) that spontaneously occurs when the operator perceives an error made by the robot or when an unexpected event occurs. We detect ERN by pre-training two linear classifiers using data collected from a preliminary experiment based on a visual reaction task. We derive the probability of failure in demand (PFD), commonly used to assess functional safety for a two-channel verification system based on the combination of linear classifiers. Functional safety analysis was then performed on a BMI-based robotic framework in which a signal was sent to the robot to active its safety measures in when an ERN was detected. Using brain-based signals, we demonstrate that it is possible to send an emergency stop action during mobile navigation task when unexpected events occur with an accuracy of 75%.     

Safety assessment of robot trajectories for navigation in uncertain and dynamic environments

This paper presents a probabilistic framework for reasoning about the safety of robot trajectories in dynamic and uncertain environments with imperfect information about the future motion of surrounding objects. For safety assessment, the overall collision probability is used to rank candidate trajectories by considering the probability of colliding with known objects as well as the estimated collision probability beyond the planning horizon. In addition, we introduce a safety assessment cost metric, the probabilistic collision cost, which considers the relative speeds and masses of multiple moving objects in which the robot may possibly collide with. The collision probabilities with other objects are estimated by probabilistic reasoning about their future motion trajectories as well as the ability of the robot to avoid them. The results are integrated into a navigation framework that generates and selects trajectories that strive to maximize safety while minimizing the time to reach a goal location. An example implementation of the proposed framework is applied to simulation scenarios, that explores some of the inherent computational trade-offs.     

基于后验概率解码段模型的汉语语音数字串识别

通过对语音解码的分析指出了基于似然概率解码的连续语音识别的局限性,并给出了三种基于后验概率段模型（Segment Model,SM）的语音解码方法.这三种方法成功地运用于随机段模型（Stochastic Segment Model,SSM）,使误识率比基线系统下降了11%;与此同时还给出了段模型的快速算法,使算法的计算复杂度降到了与隐马尔可夫模型（Hidden Markov Model,HMM）相同的数量级,满足了实用要求.     

Global localization for mobile robots using reference scan matching

This paper presents a new approach based on scan matching for global localization with a metric-topological hybrid world model. The proposed method aims to estimate relative pose to the most likely reference site by matching an input scan with reference scans, in which topological nodes are used as reference sites for pose hypotheses. In order to perform scan matching we apply the spectral scan matching (SSM) method that utilizes pairwise geometric relationships (PGR) formed by fully interconnected scan points. The SSM method allows the robot to achieve scan matching without using an initial alignment between two scans and geometric features such as corners, curves, or lines. The localization process is composed of two stages: coarse localization and fine localization. Coarse localization with 2D geometric histogram constructed from the PGR is fast, but not precise sufficiently. On the other hand, fine localization using the SSM method is comparatively slow, but more accurate. This coarse-to-fine framework reduces the computational cost, and makes the localization process reliable. The feasibility of the proposed methods is demonstrated by results of simulations and experiments.     

线性时序逻辑引导的安全强化学习

针对动态不确定环境下机器人执行复杂任务的需求,提出一种线性时序逻辑(linear temporal logic, LTL)引导的无模型安全强化学习算法,能在最大化任务完成概率的同时保证学习过程的安全性.首先,综合考虑环境中的不确定因素,构建马尔可夫决策过程(Markov decision process, MDP),再用LTL刻画智能体的复杂任务,将其转化为有多接受集的基于转移的有限确定性广义布奇自动机(transition-based limit deterministic generalized Büchi automaton, t LDGBA),并通过接受边界函数构建可记录当前待访问接受集的约束型tLDGBA (constrained tLDGBA,ctLDGBA);其次,构建乘积MDP用于强化学习搜索最优策略;最后,基于LTL对安全性的描述和MDP的观测函数构建安全博弈,并根据安全博弈设计安全盾机制保证系统在学习过程中的安全性.严格的分析证明了所提出的算法能获得最大化LTL任务完成概率的最优策略.仿真结果验证了LTL引导的安全强化学习算法的有效性.     

Towards computer support of the soft systems methodology: an evaluation of the functionality and usability of an SSM toolkit

In recent years a number of research projects have investigated computer support of the soft systems methodology (SSM). These typically involve the production of prototype computer-based tools supporting some aspects of SSM, although evaluation of these has been unsystematic and anecdotal. There has also been some debate in the literature about whether SSM is amenable to computer support. This paper reports a more systematic investigation of the potential for computer support of SSM and evaluation of the functionality and usability of an SSM support toolkit (SoftCase) developed by one of the authors. Following a brief review of previous research in this area, and the functionality of the SoftCase toolkit, the design of the evaluation and its outcome are described in detail. The paper concludes with a discussion of computer technology to support SSM and some possible directions for evaluating the impact of computer support on the SSM process.     

Asymmetric Velocity Moderation for human-safe robot control

With the increasing physical proximity of human–robot interaction, ensuring that robots do not harm surrounding humans has become crucial. Therefore, we propose asymmetric velocity moderation as a low-level controller for robotic systems to enforce human-safe motions. While our method prioritizes human safety, it also maintains the robot’s efficiency. Our proposed method restricts the robot’s speed according to (1) the displacement vector between human and robot, and (2) the robot’s velocity vector. That is to say, both the distance and the relative direction of movement are taken into account to restrict the robot’s motion. Through real-robot and simulation experiments using simplified HRI scenarios and dangerous situations, we demonstrate that our method is able to maintain the robot’s efficiency without undermining human safety.     

Evolutionary multi criteria design optimization of robot grippers

This paper explores the use of intelligent techniques to obtain optimum geometrical dimensions of a robot gripper. The optimization problem considered is a non-linear, complex, multi-constraint and multicriterion one. Three robot gripper configurations are optimized. The aim is to find Pareto optimal front for a problem that has five objective functions, nine constraints and seven variables. The problem is divided into three cases. Case 1 has first two objective functions, the case 2 considers last three objective functions and case 3 deals all the five objective functions. Intelligent optimization algorithms namely Multi-objective Genetic Algorithm (MOGA), Elitist Non-dominated Sorting Genetic Algorithm (NSGA-II) and Multi-objective Differential Evolution (MODE) are proposed to solve the problem. Normalized weighting objective functions method is used to select the best optimal solution from Pareto optimal front. Two multi-objective performance measures (solution spread measure (SSM) and ratio of non-dominated individuals (RNIs)) are used to evaluate the strength of the Pareto optimal fronts. Two more multi-objective performance measures namely optimizer overhead (OO) and algorithm effort are used to find the computational effort of MOGA, NSGA-II and MODE algorithms. The Pareto optimal fronts and results obtained from various techniques are compared and analyzed.     

Path planning of fire-escaping system for intelligent building

We present the path-planning techniques of the fire-escaping system for intelligent building, and use multiple mobile robots to present the experimental scenario. The fire-escaping system contains a supervised computer, an experimental platform, some fire-detection robots and some navigation robots. The mobile robot has the shape of a cylinder, and its diameter, height and weight are 10?cm, 15?cm and 1.5?kg, respectively. The mobile robot contains a controller module, two DC servomotors (including drivers), three IR sensor modules, a voice module and a wireless RF module. The controller of the mobile robot acquires the detection signals from reflective IR sensors through I/O pins and receives the command from the supervised computer via wireless RF interface. The fire-detection robot carries the flame sensor to detect fire sources moving on the grid-based experiment platform, and calculates the more safety escaping path using piecewise cubic Bezier curve on all probability escaping motion paths. Then the user interface uses A* searching algorithm to program escaping motion path to approach the Bezier curve on the grid-based platform. The navigation robot guides people moving to the safety area or exit door using the programmed escaping motion path. In the experimental results, the supervised computer programs the escaping paths using the proposed algorithms and presents movement scenario using the multiple smart mobile robots on the experimental platform. In the experimental scenario, the user interface transmits the motion command to the mobile robots moving on the grid-based platform, and locates the positions of fire sources by the fire-detection robots. The navigation robot guides people leaving the fire sources using the low-risk escaping motion path and moves to the exit door.     

Perception of safe robot idle time in virtual reality and real industrial environments

The main objective of this study was to investigate human perception of safe idle time of an industrial robot in a virtual reality environment. Studying operators' perception of robot operational characteristics such as safe robot idle time can help develop hazard prevention strategies, and ultimately improve robot safety. Results of data collected from 32 participants showed that robot size and speed had significant effects on the perception of safe robot idle time. This study also examined operators' perceived acceptability level for the robot speed, perceived level of hazard of robot motion, perceived chance of error, and self-reported mental workload. Results of this study were compared to the findings of Rahimi, M., Karwowski, W. [1990. Human perception of robot safe speed and idle time. Behaviour & Information Technology 9(5), 381–389], in which their experiment was conducted in a real industrial environment. This study demonstrated the feasibility of testing human perception of dynamic moving objects in a virtual reality environment. The virtual reality technology is believed to be capable of modeling a complex machinery system such as a robotic system.Relevance to industry: Human perception of the operational characteristics of industrial robots is an important concern for robot safety since misperception can cause robot operators to err, which in turn can cause injuries and fatalities. Through this study we (1) understand human perception, safety behavior, and decision making in a robotic system and (2) demonstrate the capability of modeling a complex machinery system using virtual reality technology. Our experiments designed to study human perception of safe robot idle time could lead to safety interventions and guidelines or hazard prevention strategy development.     

不同粒度下的文档分类

提出了句子空间模型及基于句子空间模型的分类算法。比较了从词、句子两个不同粒度对文档进行表示的向量空间模型和句子空间模型在对同一问题进行分类时的召回率和准确率。实验表明，与向量空间模型相比，句子空间模型在许多情况下具有较好的分类性能。     

Sequential statistical modeling method for distribution type identification

To accurately analyze behavior of mechanical system, accurate statistical modeling of input variables is necessary by identifying probabilistic distributions of input variables. These distributions are generally determined by applying goodness-of-fit (GOF) tests or model selection methods to the given data on the input variables. However, GOF tests only accept or reject the hypothesis that a candidate distribution is appropriate to represent the given data. The model selection methods determine the best-fit distribution for the given data among various candidate distributions but do not provide any information about the adequacy of using the identified distribution to represent the given data. Therefore, in this paper, a sequential statistical modeling (SSM) method is proposed. The SSM method uses a GOF test to select appropriate candidate distributions from among all possible distributions and then identifies the best-fit distribution from among the selected candidate distributions using a model selection method. The adequacy of the identified best-fit distribution is verified by using an area metric that measures the intersection area between the probability density function (PDF) of the best-fit distribution and the data distribution. This metric can be used to analyze the similarities between the PDFs of the candidate distributions. In statistical simulation tests, it was observed that the SSM method identified correct distributions more accurately and conservatively than the GOF tests or model selection methods alone.     

基于粒子滤波的智能机器人定位算法

自主定位是智能机器人的关键性技术。针对轮式智能机器人在使用里程计、激光雷达进行定位过程中存在较大误差的问题,联合双目摄像机和激光雷达数据,提出基于粒子滤波的自适应蒙特卡洛(AMCL)优化定位算法。预测阶段,利用双目摄像机和激光雷达数据改善提议分布,减少滤波过程中重采样的粒子数,用更少的粒子数来估计机器人的后验概率分布。在激光雷达匹配点云时,提出一种分组阶梯式阈值判断法,在不降低点云匹配效果的情况下,有效降低现有的迭代最近点(ICP)匹配算法的计算量。为了验证改进算法的性能,在四轮智能机器人平台上进行实验。结果表明:改进的AMCL优化定位算法可以有效提高机器人的定位精度,具有较好的实用性。     

Closed-loop safety assessment of uncertain roadmaps

The main contribution of this paper is a novel method for assessing the safety of trajectories by means of their collision probability in dynamic and uncertain environments. The future trajectories of the robot are represented as directed graphs and the uncertain states of the obstacles are represented by probability distributions. Instead of evaluating the safety of the graph by determining the route with the smallest collision probability, the optimal policy minimizing the collision probability is used. The policy allows one to replan the route depending on the future probability distributions of the obstacles. Since these distributions are unknown at the time point of the assessment, they are simulated and represented by compound probability distributions. These compound distributions represent all possible future distributions of the obstacles. It is shown that this novel method is always less conservative than previous approaches. Two example implementations are presented, one using Gaussian distributions and one using motion patterns for representing the uncertain states of the obstacles. Simulation scenarios are used for validating the proposed concept.     

A robot safety experiment varying robot speed and contrast with human decision cost

An industrial robot safety experiment was performed to find out how quickly subjects responded to an unexpected robot motion at different speeds of the robot arm, and how frequently they failed to detect a motion that should have been detected. Robotics technicians risk being fatally injured if a robot should trap them against a fixed object. The value of the experimentation lies in its ability to show that this risk can be reduced by a design change. If the robot is moving at a slow speed, during programming and troubleshooting tasks, then the worker has sufficient time to actuate an emergency stop device before the robot can reach the person. The dependent variable in the experiment was the overrun distance (beyond an expected stopping point) that a robot arm travelled before a person actuated a stop pushbutton. Results of this experiment demonstrated that the speed of the robot arm and the implied decision cost for hitting an emergency stop button had a significant effect on human reaction time. At a fairly high level of ambient lighting (560 lux), fixed-level changes in the luminance contrast between the robot arm and its background did not significantly affect human reaction time.     

Preliminary validation of two temporal parameter-based soil moisture retrieval models using a satellite product and in situ soil moisture measurements over the REMEDHUS network

This study aims to preliminarily validate two newly developed temporal parameter-based surface soil moisture (SSM) retrieval models, namely the mid-morning model and daytime model, using both microwave satellite soil moisture product and in situ SSM measurements over a well-organized soil moisture network named REd de MEDición de la HUmedad del Suelo (REMEDHUS) in Spain. Ground SSM measurements and geostationary satellite observations were primarily implemented to obtain the model coefficients for the two SSM retrieval models for each cloud-free day. These model coefficients were subsequently used to estimate SSM using the Meteosat Second Generation products over the study area. Preliminary verification using both a satellite product and in situ SSM measurements demonstrated that SSM variation can be well detected by both SSM retrieval models. Specifically, a generally similar accuracy (coefficient of determination R²: 0.419–0.379, root mean square error: 0.046–0.051 m³ m^?3, Bias: ?0.020 to ?0.025 m³ m^?3) was found for the mid-morning model and the daytime model with the microwave missions based climate change initiative SSM product, respectively. Moreover, except for the comparable R² (0.614–0.675), a better accuracy (Bias: 0.032–0.044 m³ m^?3, RMSE: 0.043–0.050 m³ m^?3) are achieved for the daytime model and the mid-morning model with network SSM measurements, respectively. These results indicate that the daytime model exhibited generally comparable or better accuracy than that of the mid-morning model over the study area. This study has strengthened the feasibility of using multi-temporal information derived from the geostationary satellites to estimate SSM in future research.