ST-SIGMA:Spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting

Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges mentioned above with a single model.To tackle this dilemma,this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting(STSIGMA),an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework.ST-SIGMA adopts a trident encoder-decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view(BEV)maps simultaneously.Specifically,an iterative aggregation network is first employed as the scene semantic encoder(SSE)to learn diverse scene information.To preserve dynamic interactions of traffic agents,ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder.Meanwhile,a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed.Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-theart(SOTA)methods in terms of scene perception and trajectory forecasting,respectively.Therefore,the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in realworld AD scenarios.

Information perception and feedback mechanism and key techniques of multi-modality human-robot interaction for service robots

With the increasing of the elderly population and the growing hearth care cost, the role of service robots in aiding the disabled and the elderly is becoming important. Many researchers in the world have paid much attention to heaRthcare robots and rehabilitation robots. To get natural and harmonious communication between the user and a service robot, the information perception/feedback ability, and interaction ability for service robots become more important in many key issues.

Connecting Language with Perception and Action for Human-robot Interaction

To build robots that engage in intuitive communication with people by natural language, we are developing a new knowledge representation called conceptual network model. The conceptual network connects natural language concepts with visual perception including color perception, shape perception, size perception, and spatial perception. In the implementation of spatial perception, we present a computational model based on spatial template theory to interpret qualitative spatial expressions. Based on the conceptual network model, our mobile robot can understand user's instructions and recognize the object referred to by the user and perform appropriate action. Experimental results show our approach promising.

Illustrating the multi-stakeholder perceptions of environmental pollution based on big data:Lessons from China

The relationship between stakeholders and the environment influences sustainable development and human wellbeing.To illustrate the multi-stakeholder perceptions of environmental pollution in China,we interpreted a feedback loop in the perception-behavior-environment nexus from the perspective of the coupled human-environment system,measured the differences of environmental perceptions among five stakeholders(the public,government,media,companies,and scientists)and regions(including 31 provinces,autonomous regions,and municipalities in China,with exceptions of Taiwan of China,Hong Kong of China,and Macao of China due to a lack of data)using big data,and made a comparison between the perceptions and the actual pollution situation.The results showed that the five stakeholders exhibited similar perceptions of environmental pollution at the national scale,with air pollution being of most concern,followed by water pollution and soil pollution.There were significant spatial differences in environmental perceptions.All stakeholders in the developed regions in eastern China paid relatively high attention to environmental issues,while those in the northwestern regions paid much less attention.There existed a mutual influence and interaction among the different stakeholders.More attention should be paid to air pollution in Xinjiang Uygur Autonomous Region and Ningxia Hui Autonomous Region,water pollution in Hainan Province,Inner Mongolia Autonomous Region,Heilongjiang Province,and Jilin Province,and soil pollution in Hainan Province,Fujian Province,and Jilin Province.This paper provides a research paradigm on multi-stakeholder environmental perceptions based on big data,and the results provide a background reference for regional environmental governance.

Computer system for simulation of human perception. Some implications for the pathophysiology of the schizophrenic syndrome

After the description of a brain model based on glial-neuronal interactions, a computer system for simulation of human perception, called clocked perception system, is proposed. The computer system includes a receptor field with sensors, each of which receives data with specific characteristics. These data are passed to processors, whereby only those connections between sensors and processors are released that are suited for an evaluation of the data according to a combination of specific data dictated by a phase program circuit. The computer system also includes a selector circuit that discards those dictated program commands that lead to a “senseless” computation result. A motor program circuit for the control of effectors may be connected to the computer system which at least contributes to the movement of the receptor field in order to bring the receptor field closer to suitable data with specific characteristics for better execution of the program. From disorders of the computer system implications are deduced for the pathophysiology of the schizophrenic syndrome. Finally, a novel treatment approach to this syndrome is proposed.

Strategies for the Interaction Design of Landscape Environment in the Information Age

The vigorous development of science and technology prompts people to put forward more diversified requirements for the built environment. The emergence of interactive landscape provides a new method for the renewal and development of landscape environment, and becomes a new way to deal with the relationship between human and landscape environment. In this paper, from the perspective of interactivity, the application achievements of interactive environmental design were analyzed from three aspects of interactive relationship, interactive forms and landscape functions, and the development space and great potential of interactivity theory in environmental design were discussed to provide reference for subsequent relevant research.

Improved Twin I-Girder Curved Bridge-Vehicle Interaction Analysis and Human Sensitivity to Vibration

The perceptible vibration of curved twin I-girder bridges under traffic loads is an important design consideration, because this bridge have rather low torsional stiffness that produce excessive vibrations. The objective of this investigation was to study the vibration of curved twin I-girder bridges due to moving vehicles and the effect of vibrations on bridge users. To this end, a comprehensive three-dimensional finite element models for bridge and vehicle are developed by using ANSYS code for studying bridge-vehicle interaction and the resultant sensitivity to vibration. Truck parameters include the body, the suspension and the tires. Gap and actuator elements are incorporated into the tire models to simulate the separation between the tires and road surface, and road surface roughness, respectively. Road roughness profiles are generated from power spectral density and cross spectral functions. To couple the motion of the bridge and vehicle, Lagrange multipliers and constraint equations are utilized through the augmented Lagrangian method. A parametric study is performed to identify the effect of various parameters on the vibration of the bridge. The results have been expressed in the form of human perceptibility curves. This study finds that the bridge response is significantly influenced by the road roughness, bump height at expansion joint and vehicle speeds. The results show that the inclusion of features such as increasing the torsional stiffness by providing additional stiffened bracing has major effects on the reduction of perceptible vibration.

Strangers in a New Land: Rural School Personnel’s Perceptions of the Implementation of an International Student Program

Many high schools in the northeastern United States have suffered from declining enrollment due to a declining population of school-age children in the region.Administrators,counselors and teachers perceive many impacts of the implementation of an international student program at a rural high school.This qualitative case study reveals that the rural high school’s unique nature impacts international student programs,international students influence both school culture and programming,and international students suffer from isolation.School leaders would benefit from considerations in the form of professional development both prior to implementation of an international student program and ongoing throughout its duration.It is important for schools to find ways to respectfully honor student cultures and optimize learning experiences.School leaders would be wise to determine desired size of international student programs and make efforts accordingly to achieve that size for optimal effectiveness for the benefit of both host and international students.Implications and recommendations for future research include further exploration of the perceived experiences of European and Chinese international students,understanding the unique nature of rural high schools and international student experiences,and examination of school practices.

Jasmonate perception: Ligand-receptor interaction, regulation, and evolution

Phytohormones integrate external environmental and developmental signals with internal cellular responses for plant survival and multiplication in changing surroundings.Jasmonate(JA),which might originate from prokaryotes and benefit plant terrestrial adaptation,is a vital phytohormone that regulates diverse developmental processes and defense responses against various environmental stresses.In this review,we first provide an overview of ligand-receptor binding techniques used for the characterization of phytohormone-receptor interactions,then introduce the identification of the receptor COI1 and active JA molecules,and finally summarize recent advances on the regulation of JA perception and its evolution.

Interaction between auditory and motor systems in speech perception

Based on the Motor Theory of speech perception, the interaction between the auditory and motor systems plays an essential role in speech perception. Since the Motor Theory was proposed, it has received remarkable attention in the field. However, each of the three hypotheses of the theory still needs further verification. In this review, we focus on how the auditory-motor anatomical and functional associations play a role in speech perception and discuss why previous studies could not reach an agreement and particularly whether the motor system involvement in speech perception is task-load dependent. Finally, we suggest that the function of the auditory-motor link is particularly useful for speech perception under adverse listening conditions and the further revised Motor Theory is a potential solution to the ＂cocktail-party＂ problem.

人智交互情境中用户对生成式人工智能的心智感知及反应研究

[目的/意义]随着AI组成技术的发展及人智协作的日趋紧密,高阶的生成式人工智能(GAI)代理具备涌现能力,通过类人化特征与用户建立社会化连接。文章旨在丰富社会技术视角下人智交互发生机理的探索,并为人本人工智能背景下GAI设计提供参考。[方法/过程]爬取豆瓣社区1275条用户与ChatGPT对话的帖子,遵循建构主义范式,基于CASA范式和心智感知理论,采用系统性主题分析方法构建框架模型。[结果/结论]构建了GAI作为社会行动者的理论框架,得到人智交互情境下用户对于GAI的心智感知及社会化反应。心智感知包括GAI主体性感知和感受性感知两种。GAI主体性感知包括创造力、可靠性、运行规则、客观性、有用性;GAI感受性感知包括共情、沟通责任、趣味性、友善、文化适应性。这两种感知会相互影响。用户对GAI的社会化反应涉及认知加工、情感唤醒、行为强化三个方面。认知加工包括知识获得、态度转变;情感唤醒包括愉悦感、共鸣、社交连接;行为强化包括持续付费行为、准社会互动。用户的社会化反应与心智感知存在双向作用关系。

基于深度表征学习和遗传算法的军用座舱色彩设计方法

军用座舱色彩设计作为载人军事设备工业设计中较为主观的一部分,设计的合理性至关重要。为提高军用座舱色彩设计的科学性,提出一种基于深度表征学习和遗传算法的军用座舱配色方法。利用深度表征学习模型预测军用座舱配色方案,并根据色彩感知理论建立军用座舱配色模型,将其作为生成方案的限制条件。同时,引入交互式遗传算法到智能配色系统中,通过人工引导的方式优化神经网络的参数,对预测的配色方案进行有效迭代。实验结果表明:该方法生成的配色方案符合军用座舱配色模型,结合遗传算法的模型预测准确率比单一的深度表征模型提高了16%~18%。相较于人工色彩设计方案,军用座舱智能配色方法生成的方案满意度略优、设计周期缩短了80%~88%,色彩稳定性提高了6%~12%。

基于社区绿地的流动人口社会融合之道——以社会交往、地方依恋为中介

社区绿地对城市流动人口社会融合的影响日益受到关注,然而目前尚不清楚社区绿地影响城市流动人口社会融合的机制和路径。利用杭州市15个社区的流动人口问卷调查数据,基于情感事件理论,以社会交往和地方依恋为中介变量,采用结构方程模型探讨了社区绿地环境感知对城市流动人口社会融合的影响机制。研究结果表明:1)社区绿地环境感知对社会交往、地方依恋有显著正向影响,对社会融合无显著影响;2)社会交往、地方依恋分别对社会融合有显著正向影响;3)社会交往、地方依恋在社区绿地环境感知与城市流动人口社会融合的关系中具有显著的部分中介效应,且社会交往的中介效应显著大于地方依恋的中介效应。研究结果丰富了流动人口社会融合的研究范畴,可为包容性城市建设提供新的决策依据。

基于时空交叉感知的实时动作检测方法

时空动作检测依赖于视频空间信息与时间信息的学习.目前,最先进的基于卷积神经网络(Convolutionsl Neural Networks,CNN)的动作检测器采用2D CNN或3D CNN架构,取得了显著的效果.然而,由于网络结构的复杂性与时空信息感知的原因,这些方法通常采用非实时、离线的方式.时空动作检测主要的挑战在于设计高效的检测网络架构,并能有效地感知融合时空特征.考虑到上述问题,本文提出了一种基于时空交叉感知的实时动作检测方法.该方法首先通过对输入视频进行乱序重排来增强时序信息,针对仅使用2D或3D骨干网络无法有效对时空特征进行建模,提出了基于时空交叉感知的多分支特征提取网络.针对单一尺度时空特征描述性不足,提出一个多尺度注意力网络来学习长期的时间依赖和空间上下文信息.针对时序和空间两种不同来源特征的融合,提出了一种新的运动显著性增强融合策略,对时空信息进行编码交叉映射,引导时序特征和空间特征之间的融合,突出更具辨别力的时空特征表示.最后,基于帧级检测器结果在线计算动作关联性链接.本文提出的方法在两个时空动作数据集UCF101-24和JHMDB-21上分别达到了84.71%和78.4%的准确率,优于现有最先进的方法,并达到73帧/秒的速度.此外,针对JHMDB-21数据集存在高类间相似性与难样本数据易于混淆等问题,本文提出了基于动作表示的关键帧光流动作检测方法,避免了冗余光流的产生,进一步提升了动作检测准确率.

感知平台卖家亲组织非伦理行为对消费者参与价值共创的影响——互动地位感知视角

基于社会相互依赖理论与应对理论,探索互动地位感知与感知平台卖家亲组织非伦理行为(Unethical Pro-organizational Behavior,UPB)对消费者参与价值共创的交互作用机制。研究结果为:互动地位感知与感知平台卖家UPB对消费者参与价值共创存在交互效应;当明确消费者互动类型时,感知平台卖家UPB与互动地位感知的交互作用消失;关系型互动→共情在平等地位感知与感知平台卖家UPB正面性交互影响消费者参与价值共创之间发挥的顺序中介效应更为显著,而交易型互动→厌恶在支配地位感知与感知平台卖家UPB负面性交互影响消费者参与价值共创之间发挥的顺序中介效应更为显著。研究结果可以帮助平台型电商组织的管理者明确互动过程中消费者对平台卖家UPB的认知、态度与行为反应,进而为平台型电商组织的治理提供一定的经验借鉴与理论指导。

基于贪婪算法的云计算数据块节能存储仿真

针对云数据储存能量消耗大的问题,提出基于贪婪算法的云计算数据块节能存储方法。建立具有用户访问层、核心服务层和服务管理层的云计算架构,了解数据块产生过程和储存环境;将物理机利用率、能源消耗量和主机储存能力作为节能储存的约束条件,将待储存的数据块封装为虚拟机,利用贪婪算法描述虚拟机部署问题,构建贪婪算法下虚拟机分配环境;计算单个物理机和整个数据中心的数据块储存能力和资源请求能力,综合考虑虚拟机分配的相关向量,运算数据储存时的能量消耗;以总体能量最小为目标函数,将虚拟机分为主模块与备用模块,通过设置虚拟机状态转换规则来减少储存开销,实现节能储存。实验结果表明,上述方法在数据储存过程中能够有效减少服务器开启数量,节省储存功率,达到节能目的。

基于激光测距仪的智能物联网体感交互感知研究

当前的智能物联网设备在识别用户指令方面存在不足,时常需要用户多次尝试,降低了用户的使用体验和对设备的信任度。为了解决问题,提出了一种基于激光测距仪的智能物联网体感交互感知方法。首先,拟合激光波绘制结果,并利用距离变换算法设定智能物联网的体感交互方式。然后,通过误差传递公式,计算激光测距仪的协方差矩阵,依据此调整参数和测量点。最后,融合激光图像特征,识别操作者的动态指令。实验结果表明,所提方法能够显著提升智能物联网设备对体感指令的采集完整度,正确完成所有体感指令,且平均体感动作类别划分精准度高达97.02%,说明所提方法具有较高的体感交互感知精度。

校园景观的情感化设计——以本科生课程教学为例

景观设计教学需要不断捕捉研究热点和探索前沿问题,并付诸教学实践。将情感价值作为建成景观的评价标准和景观设计的目标之一,以本科生“校园景观的情感化设计”学生科研培训(SRT)项目为例,通过课程的教学设计、数据解读、设计转化等过程,引导学生从本能水平、行为水平、反思水平层面理解景观的情感价值。并结合艺术院校学生的优势与特点,推导出改善景观情感价值的途径,提出校园景观的情感设计方法和策略。教学将传统的实地调研法与感知数据分析方法相结合,强调景观情感设计转化的能力。不仅探索了设计教学的方法与途径,而且提出了对景观理解的新维度和景观设计的新思路。

数字化赋能高校思政教学效果评价研究

为提升数字化赋能下高校思政教学效果,以效果评价为导向,运用文献研究法、调查法及统计分析法构建数字化赋能高校思政教学效果评价模型,并通过问卷调查收集200份数据进行验证。经t检验、探索性因子分析及验证性因子分析发现,由教师数字化教学效果评价、学生数字化学习效果评价及大数据教学效果评价构成的评价模型结果十分显著,建构合理。经多元回归分析发现,学校理念、数字技能及师生互评是影响数字化赋能下高校思政教学效果评价的三个重要因素。高校要重视数字化转型,加强对师生数字素养的培育,完善师生互评机制,形成师生互评推动下的联动向好机制,着力改进和提升高校思政教学效果。

绿洲丝路民俗交融的实践内涵、显著特征及其对当代各民族交往交流交融的启示

在以有形有感有效铸牢中华民族共同体意识的今天,从中华民族交往交流交融史、中华民族史等纵向维度展示中华民族共同体的内涵和意义,对于具有一定学科背景、知识储备的群体较为适用,但其内容过于遥远、叙事过于宏大,不易被广大民众理解和接受,需要简单通俗的语言和日常生活的参与来引导他们理解中华民族交往交流交融史的意义和价值。在聚焦绿洲丝路沿线各民族民俗融合的现实情景,以服饰民俗的共适与互动、饮食民俗的多元与共享、居住民俗的采借与创新、交通民俗的演变与互通等与民众现实生活息息相关的物质民俗为切口,横向维度透视各民族从生产、生活层面到情感、精神层面深度交融的基础上,总结衣食住行融合的鲜活性、日常性、直观性、民间性等特点,可说明交往交流交融必须落到衣食住行层面,才能因交往而得以生活,因交流得以互鉴,因交融得以共生。最后在交融加深的基础上,才能建设中华民族共同体,进而推动各民族交往交流交融回归生活本性。