农业面临着劳动危机，导致人们对小型，伪造机器人（AGBOTS）的兴趣增加，这些机器人可以执行精确的，有针对性的行动（例如，农作物侦察，除草，受精），同时由人类操作员进行监督。但是，农民不一定是机器人技术方面的专家，也不会采用增加其工作量的技术或不提供立即回报的技术。在这项工作中，我们探讨了远程人类操作员与多个Agbot之间进行通信的方法，并研究音频通信对操作员的偏好和生产率的影响。我们开发了一个模拟平台，在该平台中，AGBOT在一个字段中部署，随机遇到故障，并呼吁操作员寻求帮助。随着AGBOTS报告错误，测试了各种音频通信机制，以传达哪种机器人失败以及发生了什么类型的故障。人类的任务是在完成次要任务时口头诊断失败。进行了一项用户研究，以测试三种音频通信方法：耳塞，单短语命令和完整的句子通信。每个参与者都完成了一项调查，以确定他们的偏好和每种方法的总体效率。我们的结果表明，使用单个短语的系统是参与者最积极的看法，可以使人更有效地完成次要任务。该代码可在以下网址获得：https：//github.com/akamboj2/agbot-sim。
translated by 谷歌翻译
司机注意力预测的任务对机器人和自治车辆行业的研究人员来说具有相当大的兴趣。司机注意预测可以在缓解和防止高风险事件中起作用的乐器作用，如碰撞和伤亡。然而，现有的司机注意力预测模型忽略了驾驶员的分心状态和意图，这可能会显着影响他们如何观察周围环境。为解决这些问题，我们展示了一个新的驱动程序注意数据集，Cocatt（认知条件注意）。与以前的驱动程序注意数据集不同，CoCatt包括单帧注释，用于描述驱动程序的分散注意力状态和意图。此外，我们的数据集中的注意数据在手动和自动驾驶仪模式中使用不同分辨率的眼跟踪设备捕获。我们的结果表明，将上述两个驾驶员状态纳入注意建模可以提高驾驶员注意预测的性能。据我们所知，这项工作是第一个提供自动opilot注意数据的人。此外，COCATT目前是最大的和最多样化的驾驶员注意数据集，在自主水平，眼跟踪器分辨率和驾驶场景方面。
translated by 谷歌翻译
Intelligent agents have great potential as facilitators of group conversation among older adults. However, little is known about how to design agents for this purpose and user group, especially in terms of agent embodiment. To this end, we conducted a mixed methods study of older adults' reactions to voice and body in a group conversation facilitation agent. Two agent forms with the same underlying artificial intelligence (AI) and voice system were compared: a humanoid robot and a voice assistant. One preliminary study (total n=24) and one experimental study comparing voice and body morphologies (n=36) were conducted with older adults and an experienced human facilitator. Findings revealed that the artificiality of the agent, regardless of its form, was beneficial for the socially uncomfortable task of conversation facilitation. Even so, talkative personality types had a poorer experience with the "bodied" robot version. Design implications and supplementary reactions, especially to agent voice, are also discussed.
translated by 谷歌翻译
Gender/ing guides how we view ourselves, the world around us, and each other--including non-humans. Critical voices have raised the alarm about stereotyped gendering in the design of socially embodied artificial agents like voice assistants, conversational agents, and robots. Yet, little is known about how this plays out in research and to what extent. As a first step, we critically reviewed the case of Pepper, a gender-ambiguous humanoid robot. We conducted a systematic review (n=75) involving meta-synthesis and content analysis, examining how participants and researchers gendered Pepper through stated and unstated signifiers and pronoun usage. We found that ascriptions of Pepper's gender were inconsistent, limited, and at times discordant, with little evidence of conscious gendering and some indication of researcher influence on participant gendering. We offer six challenges driving the state of affairs and a practical framework coupled with a critical checklist for centering gender in research on artificial agents.
translated by 谷歌翻译
We study representation learning for efficient imitation learning over linear systems. In particular, we consider a setting where learning is split into two phases: (a) a pre-training step where a shared $k$-dimensional representation is learned from $H$ source policies, and (b) a target policy fine-tuning step where the learned representation is used to parameterize the policy class. We find that the imitation gap over trajectories generated by the learned target policy is bounded by $\tilde{O}\left( \frac{k n_x}{HN_{\mathrm{shared}}} + \frac{k n_u}{N_{\mathrm{target}}}\right)$, where $n_x > k$ is the state dimension, $n_u$ is the input dimension, $N_{\mathrm{shared}}$ denotes the total amount of data collected for each policy during representation learning, and $N_{\mathrm{target}}$ is the amount of target task data. This result formalizes the intuition that aggregating data across related tasks to learn a representation can significantly improve the sample efficiency of learning a target task. The trends suggested by this bound are corroborated in simulation.
translated by 谷歌翻译
Autonomous navigation in crowded spaces poses a challenge for mobile robots due to the highly dynamic, partially observable environment. Occlusions are highly prevalent in such settings due to a limited sensor field of view and obstructing human agents. Previous work has shown that observed interactive behaviors of human agents can be used to estimate potential obstacles despite occlusions. We propose integrating such social inference techniques into the planning pipeline. We use a variational autoencoder with a specially designed loss function to learn representations that are meaningful for occlusion inference. This work adopts a deep reinforcement learning approach to incorporate the learned representation for occlusion-aware planning. In simulation, our occlusion-aware policy achieves comparable collision avoidance performance to fully observable navigation by estimating agents in occluded spaces. We demonstrate successful policy transfer from simulation to the real-world Turtlebot 2i. To the best of our knowledge, this work is the first to use social occlusion inference for crowd navigation.
translated by 谷歌翻译
单词错误率（WER）是用于评估自动语音识别（ASR）模型质量的主要度量。已经表明，与典型的英语说话者相比，ASR模型的语音障碍者的扬声器往往更高。在如此高的错误率下，很难确定模型是否可以很有用。这项研究调查了BertScore的使用，BertScore是文本生成的评估指标，以提供对ASR模型质量和实用性的更有信息度量。将Bertscore和WER与语言病理学家手动注释以进行错误类型和评估手动注释的预测错误。发现Bertscore与人类的误差类型和评估评估更相关。在保留含义的拼字法变化（收缩和归一化误差）上，Bertscore特别强大。此外，使用顺序逻辑回归和Akaike的信息标准（AIC）测量，Bertscore比WER更好地评估了错误评估。总体而言，我们的发现表明，从实际角度评估ASR模型性能时，Bertscore可以补充，尤其是对于可访问性应用程序，即使模型的精度也比典型语音较低的模型也很有用。
translated by 谷歌翻译
当人类与机器人互动时，不可避免地会影响。考虑一辆在人类附近行驶的自动驾驶汽车：自动驾驶汽车的速度和转向将影响人类驾驶方式。先前的作品开发了框架，使机器人能够影响人类对所需行为的影响。但是，尽管这些方法在短期（即前几个人类机器人相互作用）中有效，但我们在这里探索了长期影响（即同一人与机器人之间的重复相互作用）。我们的主要见解是，人类是动态的：人们适应机器人，一旦人类学会预见机器人的行为，现在影响力的行为可能会失败。有了这种见解，我们在实验上证明了一种普遍的游戏理论形式主义，用于产生有影响力的机器人行为，而不是重复互动的有效性降低。接下来，我们为Stackelberg游戏提出了三个修改，这些游戏使机器人的政策具有影响力和不可预测性。我们最终在模拟和用户研究中测试了这些修改：我们的结果表明，故意使他们的行为更难预期的机器人能够更好地维持对长期互动的影响。在此处查看视频：https：//youtu.be/ydo83cgjz2q
translated by 谷歌翻译
由于大规模数据集的可用性，通常在特定位置和良好的天气条件下收集的大规模数据集，近年来，自动驾驶汽车的感知进展已加速。然而，为了达到高安全要求，这些感知系统必须在包括雪和雨在内的各种天气条件下进行稳健运行。在本文中，我们提出了一个新数据集，以通过新颖的数据收集过程启用强大的自动驾驶 - 在不同场景（Urban，Highway，乡村，校园），天气，雪，雨，阳光下，沿着15公里的路线反复记录数据），时间（白天/晚上）以及交通状况（行人，骑自行车的人和汽车）。该数据集包括来自摄像机和激光雷达传感器的图像和点云，以及高精度GPS/ins以在跨路线上建立对应关系。该数据集包括使用Amodal掩码捕获部分遮挡和3D边界框的道路和对象注释。我们通过分析基准在道路和对象，深度估计和3D对象检测中的性能来证明该数据集的独特性。重复的路线为对象发现，持续学习和异常检测打开了新的研究方向。链接到ITHACA365：https：//ithaca365.mae.cornell.edu/
translated by 谷歌翻译
在无人车的领域，自主机器人群体承诺将提高效率和集体自主权。这些群体将来将如何运作，以及尚未充分定义这些沟通要求和运营界限。与11位专业的无人车运营商和设计师进行了研讨会，目的是确定用于开发和测试机器人群的用例。专家定义了三个方案，然后编译以生产一个用例，概述与高度自主群合作时的情况，目标，代理，通信要求和操作阶段。我们的编译用例均适用于研究人员，设计师和制造商，以测试和量身定制其设计管道，以适应人类互动的一些关键问题。应用程序的示例包括告知模拟开发，构成进一步设计研讨会的基础，并确定人类运营商与群体之间可能出现的信任问题。
translated by 谷歌翻译