基于模拟的推理的现代方法依赖于深度学习代理来实现与计算机模拟器的近似推断。在实践中，估计的后代的计算忠诚度很少得到保证。例如，Hermans等。 （2021）表明，当前基于仿真的推理算法可以产生过度自信的后代，因此可能会出现虚假推断。在这项工作中，我们引入了平衡的神经比估计（BNRE），该算法的变体旨在产生后近似值，往往更保守，从而提高了其可靠性，同时共享同样的贝叶斯最佳解决方案。我们通过执行平衡条件来实现这一目标，从而增加了小型模拟预算制度中的量化不确定性，同时仍会随着预算的增加而融合到确切的后部。我们提供的理论论点表明，BNRE倾向于产生比NRE更保守的后替代物。我们对BNRE进行了多种任务的评估，并表明它在所有测试的基准和仿真预算上产生了保守的后验代替代物。最后，我们强调BNRE可以直接实施NRE，并且不引入任何计算开销。

We present extensive empirical evidence showing that current Bayesian simulation-based inference algorithms can produce computationally unfaithful posterior approximations. Our results show that all benchmarked algorithms -- (Sequential) Neural Posterior Estimation, (Sequential) Neural Ratio Estimation, Sequential Neural Likelihood and variants of Approximate Bayesian Computation -- can yield overconfident posterior approximations, which makes them unreliable for scientific use cases and falsificationist inquiry. Failing to address this issue may reduce the range of applicability of simulation-based inference. For this reason, we argue that research efforts should be made towards theoretical and methodological developments of conservative approximate inference algorithms and present research directions towards this objective. In this regard, we show empirical evidence that ensembling posterior surrogates provides more reliable approximations and mitigates the issue.

Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton formats provided by different datasets, i.e., they do not label the same set of anatomical landmarks. There is little prior research on how to best supervise one model with such discrepant labels. We show that simply using separate output heads for different skeletons results in inconsistent depth estimates and insufficient information sharing across skeletons. As a remedy, we propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. The discovered latent 3D points capture the redundancy among skeletons, enabling enhanced information sharing when used for consistency regularization. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset. Our code and models are available for research purposes.

Reliably planning fingertip grasps for multi-fingered hands lies as a key challenge for many tasks including tool use, insertion, and dexterous in-hand manipulation. This task becomes even more difficult when the robot lacks an accurate model of the object to be grasped. Tactile sensing offers a promising approach to account for uncertainties in object shape. However, current robotic hands tend to lack full tactile coverage. As such, a problem arises of how to plan and execute grasps for multi-fingered hands such that contact is made with the area covered by the tactile sensors. To address this issue, we propose an approach to grasp planning that explicitly reasons about where the fingertips should contact the estimated object surface while maximizing the probability of grasp success. Key to our method's success is the use of visual surface estimation for initial planning to encode the contact constraint. The robot then executes this plan using a tactile-feedback controller that enables the robot to adapt to online estimates of the object's surface to correct for errors in the initial plan. Importantly, the robot never explicitly integrates object pose or surface estimates between visual and tactile sensing, instead it uses the two modalities in complementary ways. Vision guides the robots motion prior to contact; touch updates the plan when contact occurs differently than predicted from vision. We show that our method successfully synthesises and executes precision grasps for previously unseen objects using surface estimates from a single camera view. Further, our approach outperforms a state of the art multi-fingered grasp planner, while also beating several baselines we propose.

Robots operating in human environments must be able to rearrange objects into semantically-meaningful configurations, even if these objects are previously unseen. In this work, we focus on the problem of building physically-valid structures without step-by-step instructions. We propose StructDiffusion, which combines a diffusion model and an object-centric transformer to construct structures out of a single RGB-D image based on high-level language goals, such as "set the table." Our method shows how diffusion models can be used for complex multi-step 3D planning tasks. StructDiffusion improves success rate on assembling physically-valid structures out of unseen objects by on average 16% over an existing multi-modal transformer model, while allowing us to use one multi-task model to produce a wider range of different structures. We show experiments on held-out objects in both simulation and on real-world rearrangement tasks. For videos and additional results, check out our website: http://weiyuliu.com/StructDiffusion/.

物体很少在人类环境中孤立地坐着。因此，我们希望我们的机器人来推理多个对象如何相互关系，以及这些关系在机器人与世界互动时可能会发生变化。为此，我们提出了一个新型的图形神经网络框架，用于多对象操纵，以预测对机器人行动的影响如何变化。我们的模型在部分视图点云上运行，可以推理操作过程中动态交互的多个对象。通过在学习的潜在图嵌入空间中学习动态模型，我们的模型使多步规划可以达到目标目标关系。我们展示了我们的模型纯粹是在模拟中训练的，可以很好地传输到现实世界。我们的计划器使机器人能够使用推送和拾取和地点技能重新排列可变数量的对象。

3D姿势估计对于分析和改善人体机器人相互作用的人体工程学和降低肌肉骨骼疾病的风险很重要。基于视觉的姿势估计方法容易出现传感器和模型误差以及遮挡，而姿势估计仅来自相互作用的机器人的轨迹，却遭受了模棱两可的解决方案。为了从两种方法的优势中受益并改善了它们的弊端，我们引入了低成本，非侵入性和遮挡刺激性多感应3D姿势估计算法中的物理人类手机相互作用。我们在单个相机上使用openpose的2D姿势，以及人类执行任务时相互作用的机器人的轨迹。我们将问题建模为部分观察的动力学系统，并通过粒子滤波器推断3D姿势。我们介绍了远程操作的工作，但可以将其推广到其他人类机器人互动的其他应用。我们表明，我们的多感官系统比仅使用机器人的轨迹仅使用openpose或姿势估计的姿势估计来更好地解决人运动冗余。与金标准运动捕获姿势相比，这将提高估计姿势的准确性。此外，当使用Rula评估工具进行姿势评估时，我们的方法也比其他单一感觉方法更好。

我们提出了一种新的注意机制，称为全球分层注意（GHA），用于3D点云分析。 GHA通过在多个层次结构上进行一系列粗化和插值操作，近似于常规的全局点产生关注。 GHA的优势是两个方面。首先，它相对于点数具有线性复杂性，从而使大点云的处理能够处理。其次，GHA固有地具有归纳性偏见，可以专注于空间接近点，同时保留所有点之间的全球连通性。与前馈网络相结合，可以将GHA插入许多现有的网络体系结构中。我们尝试多个基线网络，并表明添加GHA始终如一地提高不同任务和数据集的性能。对于语义分割的任务，GHA在扫描板上的Minkowskiengine基线增加了1.7％的MIOU。对于3D对象检测任务，GHA将CenterPoint基线提高了Nuscenes数据集上的 +0.5％地图，而3DETR基线将SCANNET上的基线提高到 +2.1％MAP25和 +1.5％MAP50。

由于其在建模复杂操作方面的性能和灵活性，变压器在计算机视觉中变得普遍。特别重要的是“交叉注意”操作，它允许通过参与任意大小的输入功能集来学习一个向量表示（例如，图像中的对象）。最近，提出了“掩盖注意力”，其中给定的对象表示仅关注那些对象的分割掩码处于活动状态的图像像素功能。这种注意力的专业证明对各种图像和视频细分任务有益。在本文中，我们提出了另一种专业化的注意力，该专业能够通过“软遮罩”（具有连续遮罩概率而不是二进制值的那些软遮罩）参加，并且通过这些掩码概率也可以差异化，从而允许学习掩模用于注意的掩模。在网络中无需直接损失监督。这对于多种应用程序可能很有用。具体而言，我们对弱监督视频对象细分（VOS）的任务采用了“可区分的软掩盖注意力”，在该任务中，我们为VOS开发了一个基于变压器的网络，该网络仅需要单个带注释的图像框架，但也可以仅带有一个带注释的框架的视频中的循环一致性培训受益。尽管没有标记的框架中的口罩没有损失，但由于我们的新型注意力表述，该网络仍然能够在这些框架中细分对象。代码：https：//github.com/ali2500/hodor/blob/main/main/hodor/modelling/encoder/soft_masked_attention.py

用于视频对象分割（VOS）的现有最先进方法（VOS）学习帧之间的低级像素到像素对应关系，以在视频中传播对象掩码。这需要大量的密集注释的视频数据，这是昂贵的注释，并且由于视频内的帧是高度相关的，因此由于视频内的帧具有很大冗余。鉴于此，我们提出了HODOR：一种新的方法，通过有效地利用被帮助的静态图像来理解对象外观和场景上下文来解决VOS的新方法。我们将来自图像帧的对象实例和场景信息编码为强大的高级描述符，然后可以用于重新划分不同帧中的这些对象。因此，与没有视频注释培训的现有方法相比，HODOR在DAVIS和YOUTUBE-VOS基准上实现了最先进的性能。如果没有任何架构修改，HODOR也可以通过利用循环一致性围绕单个注释的视频帧周围的视频上下文学习，而其他方法依赖于密集，则时间上一致的注释。