许多生物,包括各种种类的蜘蛛和毛毛虫,都会改变其形状以切换步态并适应不同的环境。从可拉伸电路到高度变形的软机器人,最近的技术进步已经开始使变化的机器人成为可能。但是,目前尚不清楚应如何以及何时发生变化以及可以获得哪些功能,从而导致各种未解决的设计和控制问题。为了开始解决这些问题,我们在这里模拟,设计和构建一个软机器人,该机器人利用形状变化来在平坦和倾斜的表面上实现运动。在模拟中对该机器人进行建模,我们在两个环境中探索了它的功能,并证明了特定于环境特定形状和步态的存在,这些形状和步态成功地转移到了物理硬件中。我们发现,改变形状的机器人在模拟和现实中比等效但不正确的机器人更好地遍历这些环境。
translated by 谷歌翻译
When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features into a single objective. If they try to do both at once from input designed to teach the full reward function, it is easy to end up with a representation that contains spurious correlations in the data, which fails to generalize to new settings. Instead, our ultimate goal is to enable robots to identify and isolate the causal features that people actually care about and use when they represent states and behavior. Our idea is that we can tune into this representation by asking users what behaviors they consider similar: behaviors will be similar if the features that matter are similar, even if low-level behavior is different; conversely, behaviors will be different if even one of the features that matter differs. This, in turn, is what enables the robot to disambiguate between what needs to go into the representation versus what is spurious, as well as what aspects of behavior can be compressed together versus not. The notion of learning representations based on similarity has a nice parallel in contrastive learning, a self-supervised representation learning technique that maps visually similar data points to similar embeddings, where similarity is defined by a designer through data augmentation heuristics. By contrast, in order to learn the representations that people use, so we can learn their preferences and objectives, we use their definition of similarity. In simulation as well as in a user study, we show that learning through such similarity queries leads to representations that, while far from perfect, are indeed more generalizable than self-supervised and task-input alternatives.
translated by 谷歌翻译
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. Furthermore, we show that PACL is also applicable to image-level predictions and when used with a CLIP backbone, provides a general improvement in zero-shot classification accuracy compared to CLIP, across a suite of 12 image classification datasets.
translated by 谷歌翻译
在图像分类中,在检测分布(OOD)数据时发生了许多发展。但是,大多数OOD检测方法是在一组标准数据集上评估的,该数据集与培训数据任意不同。没有明确的定义``好的''ood数据集。此外,最先进的OOD检测方法已经在这些标准基准上取得了几乎完美的结果。在本文中,我们定义了2类OOD数据使用与分布(ID)数据的感知/视觉和语义相似性的微妙概念。我们将附近的OOD样本定义为感知上相似但语义上与ID样本的不同,并将样本转移为视觉上不同但在语义上与ID相似的点数据。然后,我们提出了一个基于GAN的框架,用于从这两个类别中生成OOD样品,给定一个ID数据集。通过有关MNIST,CIFAR-10/100和Imagenet的广泛实验,我们表明A)在常规基准上表现出色的ART OOD检测方法对我们提出的基准测试的稳健性明显较小。 N基准测试,反之亦然,因此表明甚至可能不需要单独的OOD集来可靠地评估OOD检测中的性能。
translated by 谷歌翻译
The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. However, obtaining annotations is expensive and requires great effort, which is especially challenging for videos. Moreover, the use of human-generated annotations leads to models with biased learning and poor domain generalization and robustness. As an alternative, self-supervised learning provides a way for representation learning which does not require annotations and has shown promise in both image and video domains. Different from the image domain, learning video representations are more challenging due to the temporal dimension, bringing in motion and other environmental dynamics. This also provides opportunities for video-exclusive ideas that advance self-supervised learning in the video and multimodal domain. In this survey, we provide a review of existing approaches on self-supervised learning focusing on the video domain. We summarize these methods into four different categories based on their learning objectives: 1) pretext tasks, 2) generative learning, 3) contrastive learning, and 4) cross-modal agreement. We further introduce the commonly used datasets, downstream evaluation tasks, insights into the limitations of existing works, and the potential future directions in this area.
translated by 谷歌翻译
在本文中,我们为Pavlovian信号传达的多方面的研究 - 一个过程中学到的一个过程,一个代理商通过另一个代理商通知决策的时间扩展预测。信令紧密连接到时间和时间。在生成和接收信号的服务中,已知人类和其他动物代表时间,确定自过去事件以来的时间,预测到未来刺激的时间,并且都识别和生成展开时间的模式。我们调查通过引入部分可观察到的决策域来对学习代理之间的影响和信令在我们称之为霜冻空心的情况下如何影响学习代理之间的影响和信令。在该域中,预测学习代理和加强学习代理被耦合到两部分决策系统,该系统可以在避免时间条件危险时获取稀疏奖励。我们评估了两个域变型:机器代理在七态线性步行中交互,以及虚拟现实环境中的人机交互。我们的结果展示了帕夫洛维亚信号传导的学习速度,对药剂 - 代理协调具有不同时间表示(并且不)的影响,以及颞次锯齿对药剂和人毒剂相互作用的影响方式不同。作为主要贡献,我们将Pavlovian信号传导为固定信号范例与两个代理之间完全自适应通信学习之间的天然桥梁。我们进一步展示了如何从固定的信令过程计算地构建该自适应信令处理,其特征在于,通过快速的连续预测学习和对接收信号的性质的最小限制。因此,我们的结果表明了加固学习代理之间的沟通学习的可行建设者的途径。
translated by 谷歌翻译
本文解决了现场机器人动态运动下动态在线估计和3轴磁力计的硬铁和软铁偏置的动态在线估计和补偿问题,利用了3轴磁力计和3轴角度的偏置测量速率传感器。所提出的磁力计和角速度偏差估计器(MAVBE)利用了对经受角速度偏移的磁力计信号的非线性处理动态的15状态过程模型,同时估计9个磁力计偏置参数和3个角速率传感器偏置参数,在扩展卡尔曼过滤器框架。偏置参数局部可操作性在数值评估。偏置补偿信号与3轴加速度计信号一起用于估计偏置补偿磁力大地测量标题。与Chesapeake Bay,MD,MD,MD,MD,MD,MD,MD,MD,MD的数值模拟,实验室实验和全规模场试验中,评估了所提出的MAVBE方法的性能。对于所提出的Mavbe,(i)仪器态度不需要估计偏差,结果表明(ii)偏差是本地可观察的,(iii)偏差估计迅速收敛到真正的偏置参数,(iv)仅适用于适度的仪器偏压估计收敛需要激发,并且(v)对磁力计硬铁和柔软铁偏差的补偿显着提高了动态前线估计精度。
translated by 谷歌翻译
人工智能系统越来越涉及持续学习,以实现在系统培训期间不遇到的一般情况下的灵活性。与自治系统的人类互动广泛研究,但在系统积极学习的同时,研究发生了迄今为止发生的互动,并且可以在几分钟内明显改变其行为。在这项试验研究中,我们调查如何在代理商发展能力时如何发展人类和不断学习的预测代理人之间的互动。此外,我们可以比较两个不同的代理架构来评估代理设计中的代表性选择如何影响人工代理交互。我们开发虚拟现实环境和基于时间的预测任务,其中从增强学习(RL)算法增强人类预测中学到的预测。我们评估参与者在此任务中的性能和行为如何在代理类型中不同,使用定量和定性分析。我们的研究结果表明,系统的人类信任可能受到与代理人的早期互动的影响,并且反过来的信任会影响战略行为,但试点研究的限制排除了任何结论的声明。我们将信任作为互动的关键特征,以考虑基于RL的技术在考虑基于RL的技术时,并对这项研究进行了几项建议,以准备更大规模的调查。本文的视频摘要可以在https://youtu.be/ovyjdnbqtwq找到。
translated by 谷歌翻译
我们提供了PelficGridWorld软件包,为用户提供轻量级,模块化和可定制的框架,用于创建专注的电源系统的多代理体育馆环境,该环境易于与强化学习(RL)的现有培训框架集成。虽然存在许多框架用于训练多代理RL(MARL)政策,但没有可以快速原型并发开发环境,尤其是在所需电流解决方案来定义网格的异构(复合式,多器件)电力系统的背景下 - 级别变量和成本。 PowerGridWorld是一个开源软件包,有助于填补此间隙。为了突出PowerGridWorld的关键功能,我们展示了两个案例研究,并使用Openai的多代理深度确定性政策梯度(MADDPG)和RLLIB的近端策略优化(PPO)算法来演示MARL政策。在这两种情况下,至少一些代理子集合在每次作为奖励(负成本)结构的一部分中的一部分中的功率流溶液的元件。
translated by 谷歌翻译
毒性言论,也被称为仇恨言论,被认为是今天批评在线社交媒体的重要问题之一。最近关于有毒语音检测的工作受到文本的模型,没有现有的毒性检测从口语中的出口检测。在本文中,我们提出了一种从口语中检测毒性的新口语处理任务。我们介绍了排毒,这是英语演讲的第一个公开的毒性注释数据集,来自各种公开可用的语音数据库,包括超过200万个话语。最后,我们还提供了对毒性注释的语音语料库的分析可以帮助促进E2E模型的发展,更好地捕获语音中的各种韵律线索,从而提高了口语的毒性分类。
translated by 谷歌翻译