软气动执行器已经在许多软机器人系统中看到了应用，其压力驱动的性质提出了控制其运动的独特挑战和机会。在这项工作中，我们提出了一个新概念：通过末端几何形状设计和控制气动执行器。我们演示了一个新颖的执行器类，称为折叠气动人造肌肉（Foldpam），该肌肉具有一个薄纤维的空气袋，两侧对称折叠。改变执行器的折叠部分会改变最终约束，从而改变力 - 应变关系。我们通过测量具有各种长度和折叠量的单个foldpam单元的力 - 应变关系来实验研究这一变化。除静态几何单元外，驱动的FOLDPAM设备还设计为产生末端几何形状的连续，按需调整，从而实现闭环位置控制，同时保持恒定压力。使用设备的实验表明几何控制允许进入力 - 应变平面上的不同区域，并且闭环几何控制可以在驱动范围的0.5％以内实现误差。

We outline our work on evaluating robots that assist older adults by engaging with them through multiple modalities that include physical interaction. Our thesis is that to increase the effectiveness of assistive robots: 1) robots need to understand and effect multimodal actions, 2) robots should not only react to the human, they need to take the initiative and lead the task when it is necessary. We start by briefly introducing our proposed framework for multimodal interaction and then describe two different experiments with the actual robots. In the first experiment, a Baxter robot helps a human find and locate an object using the Multimodal Interaction Manager (MIM) framework. In the second experiment, a NAO robot is used in the same task, however, the roles of the robot and the human are reversed. We discuss the evaluation methods that were used in these experiments, including different metrics employed to characterize the performance of the robot in each case. We conclude by providing our perspective on the challenges and opportunities for the evaluation of assistive robots for older adults in realistic settings.

The distributed representation of symbols is one of the key technologies in machine learning systems today, playing a pivotal role in modern natural language processing. Traditional word embeddings associate a separate vector with each word. While this approach is simple and leads to good performance, it requires a lot of memory for representing a large vocabulary. To reduce the memory footprint, the default embedding layer in spaCy is a hash embeddings layer. It is a stochastic approximation of traditional embeddings that provides unique vectors for a large number of words without explicitly storing a separate vector for each of them. To be able to compute meaningful representations for both known and unknown words, hash embeddings represent each word as a summary of the normalized word form, subword information and word shape. Together, these features produce a multi-embedding of a word. In this technical report we lay out a bit of history and introduce the embedding methods in spaCy in detail. Second, we critically evaluate the hash embedding architecture with multi-embeddings on Named Entity Recognition datasets from a variety of domains and languages. The experiments validate most key design choices behind spaCy's embedders, but we also uncover a few surprising results.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

Most research on task oriented dialog modeling is based on written text input. However, users interact with practical dialog systems often using speech as input. Typically, systems convert speech into text using an Automatic Speech Recognition (ASR) system, introducing errors. Furthermore, these systems do not address the differences in written and spoken language. The research on this topic is stymied by the lack of a public corpus. Motivated by these considerations, our goal in hosting the speech-aware dialog state tracking challenge was to create a public corpus or task which can be used to investigate the performance gap between the written and spoken forms of input, develop models that could alleviate this gap, and establish whether Text-to-Speech-based (TTS) systems is a reasonable surrogate to the more-labor intensive human data collection. We created three spoken versions of the popular written-domain MultiWoz task -- (a) TTS-Verbatim: written user inputs were converted into speech waveforms using a TTS system, (b) Human-Verbatim: humans spoke the user inputs verbatim, and (c) Human-paraphrased: humans paraphrased the user inputs. Additionally, we provided different forms of ASR output to encourage wider participation from teams that may not have access to state-of-the-art ASR systems. These included ASR transcripts, word time stamps, and latent representations of the audio (audio encoder outputs). In this paper, we describe the corpus, report results from participating teams, provide preliminary analyses of their results, and summarize the current state-of-the-art in this domain.

The automated machine learning (AutoML) field has become increasingly relevant in recent years. These algorithms can develop models without the need for expert knowledge, facilitating the application of machine learning techniques in the industry. Neural Architecture Search (NAS) exploits deep learning techniques to autonomously produce neural network architectures whose results rival the state-of-the-art models hand-crafted by AI experts. However, this approach requires significant computational resources and hardware investments, making it less appealing for real-usage applications. This article presents the third version of Pareto-Optimal Progressive Neural Architecture Search (POPNASv3), a new sequential model-based optimization NAS algorithm targeting different hardware environments and multiple classification tasks. Our method is able to find competitive architectures within large search spaces, while keeping a flexible structure and data processing pipeline to adapt to different tasks. The algorithm employs Pareto optimality to reduce the number of architectures sampled during the search, drastically improving the time efficiency without loss in accuracy. The experiments performed on images and time series classification datasets provide evidence that POPNASv3 can explore a large set of assorted operators and converge to optimal architectures suited for the type of data provided under different scenarios.

Quantifying the perceptual similarity of two images is a long-standing problem in low-level computer vision. The natural image domain commonly relies on supervised learning, e.g., a pre-trained VGG, to obtain a latent representation. However, due to domain shift, pre-trained models from the natural image domain might not apply to other image domains, such as medical imaging. Notably, in medical imaging, evaluating the perceptual similarity is exclusively performed by specialists trained extensively in diverse medical fields. Thus, medical imaging remains devoid of task-specific, objective perceptual measures. This work answers the question: Is it necessary to rely on supervised learning to obtain an effective representation that could measure perceptual similarity, or is self-supervision sufficient? To understand whether recent contrastive self-supervised representation (CSR) may come to the rescue, we start with natural images and systematically evaluate CSR as a metric across numerous contemporary architectures and tasks and compare them with existing methods. We find that in the natural image domain, CSR behaves on par with the supervised one on several perceptual tests as a metric, and in the medical domain, CSR better quantifies perceptual similarity concerning the experts' ratings. We also demonstrate that CSR can significantly improve image quality in two image synthesis tasks. Finally, our extensive results suggest that perceptuality is an emergent property of CSR, which can be adapted to many image domains without requiring annotations.

In this paper we propose new probabilistic and dynamic (adaptive) strategies to create multi-method ensembles based on the Coral Reefs Optimization with Substrate Layers (CRO-SL) algorithm. The CRO-SL is an evolutionary-based ensemble approach, able to combine different search procedures within a single population. In this work we discuss two different probabilistic strategies to improve the algorithm. First, we defined the Probabilistic CRO-SL (PCRO-SL), which substitutes the substrates in the CRO-SL population by {\em tags} associated with each individual. Each tag represents a different operator which will modify the individual in the reproduction phase. In each generation of the algorithm, the tags are randomly assigned to the individuals with a similar probability, obtaining this way an ensemble with a more intense change in the application of different operators to a given individual than the original CRO-SL. The second strategy discussed in this paper is the Dynamical Probabilistic CRO-SL (DPCRO-SL), in which the probability of tag assignment is modified during the evolution of the algorithm, depending on the quality of the solutions generated in each substrate. Thus, the best substrates in the search process will be assigned with a higher probability that those which showed a worse performance during the search. We test the performance of the proposed probabilistic and dynamic ensembles in different optimization problems, including benchmark functions and a real application of wind turbines layout optimization, comparing the results obtained with that of existing algorithms in the literature.

Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements. Recent efforts, therefore, focus on collecting person-related datasets that have carefully selected labels, including sensitive characteristics, and consent forms in place to use those attributes for model testing and development. Responsible data collection involves several stages, including but not limited to determining use-case scenarios, selecting categories (annotations) such that the data are fit for the purpose of measuring algorithmic bias for subgroups and most importantly ensure that the selected categories/subcategories are robust to regional diversities and inclusive of as many subgroups as possible. Meta, in a continuation of our efforts to measure AI algorithmic bias and robustness (https://ai.facebook.com/blog/shedding-light-on-fairness-in-ai-with-a-new-data-set), is working on collecting a large consent-driven dataset with a comprehensive list of categories. This paper describes our proposed design of such categories and subcategories for Casual Conversations v2.

在本文中，我们研究了DRL算法在本地导航问题的应用，其中机器人仅配备有限​​量距离的外部感受传感器（例如LIDAR），在未知和混乱的工作区中朝着目标位置移动。基于DRL的碰撞避免政策具有一些优势，但是一旦他们学习合适的动作的能力仅限于传感器范围，它们就非常容易受到本地最小值的影响。由于大多数机器人在非结构化环境中执行任务，因此寻求能够避免本地最小值的广义本地导航政策，尤其是在未经训练的情况下，这是非常兴趣的。为此，我们提出了一种新颖的奖励功能，该功能结合了在训练阶段获得的地图信息，从而提高了代理商故意最佳行动方案的能力。另外，我们使用SAC算法来训练我们的ANN，这表明在最先进的文献中比其他人更有效。一组SIM到SIM和SIM到现实的实验表明，我们提出的奖励与SAC相结合的表现优于比较局部最小值和避免碰撞的方法。