倒置摆是一种非线性不平衡系统,需要使用电动机控制以实现稳定性和平衡。倒置摆用乐高构建,并使用乐高思维NXT,这是一种可编程机器人,能够完成许多不同的功能。在本文中,提出了倒置摆的初始设计,研究了与乐高思维NXT兼容的不同传感器的性能。此外,还研究了计算机视觉实现维持系统所需的稳定性的能力。倒置摆是一种传统推车,可以使用模糊逻辑控制器来控制,该模糊逻辑控制器为推车产生自调谐PID控制以继续前进。模糊逻辑和PID在Matlab和Simulink中模拟,并且在LabVIEW软件中开发了机器人的程序。
translated by 谷歌翻译
本文的目的是描述一种在实时反馈中检测滑动和接触力的方法。在这种新颖的方法中,戴维斯相机由于其快速处理速度和高分辨率而被用作视觉触觉传感器。在具有不同形状,尺寸,重量和材料的四个物体上进行两百实验,以比较Baxter机器人夹持器的精度和响应以避免滑动。通过使用力敏感电阻(FSR402)验证了先进的方法。使用Davis Camera捕获的事件通过特定算法处理,以向允许其检测滑动的Baxter Robot提供反馈。
translated by 谷歌翻译
In this paper, we present a novel control architecture for the online adaptation of bipedal locomotion on inclined obstacles. In particular, we introduce a novel, cost-effective, and versatile foot sensor to detect the proximity of the robot's feet to the ground (bump sensor). By employing this sensor, feedback controllers are implemented to reduce the impact forces during the transition of the swing to stance phase or steeping on inclined unseen obstacles. Compared to conventional sensors based on contact reaction force, this sensor detects the distance to the ground or obstacles before the foot touches the obstacle and therefore provides predictive information to anticipate the obstacles. The controller of the proposed bump sensor interacts with another admittance controller to adjust leg length. The walking experiments show successful locomotion on the unseen inclined obstacle without reducing the locomotion speed with a slope angle of 12. Foot position error causes a hard impact with the ground as a consequence of accumulative error caused by links and connections' deflection (which is manufactured by university tools). The proposed framework drastically reduces the feet' impact with the ground.
translated by 谷歌翻译
We introduce a new probabilistic temporal logic for the verification of Markov Decision Processes (MDP). Our logic is the first to include operators for causal reasoning, allowing us to express interventional and counterfactual queries. Given a path formula $\phi$, an interventional property is concerned with the satisfaction probability of $\phi$ if we apply a particular change $I$ to the MDP (e.g., switching to a different policy); a counterfactual allows us to compute, given an observed MDP path $\tau$, what the outcome of $\phi$ would have been had we applied $I$ in the past. For its ability to reason about different configurations of the MDP, our approach represents a departure from existing probabilistic temporal logics that can only reason about a fixed system configuration. From a syntactic viewpoint, we introduce a generalized counterfactual operator that subsumes both interventional and counterfactual probabilities as well as the traditional probabilistic operator found in e.g., PCTL. From a semantics viewpoint, our logic is interpreted over a structural causal model (SCM) translation of the MDP, which gives us a representation amenable to counterfactual reasoning. We provide a proof-of-concept evaluation of our logic on a reach-avoid task in a grid-world model.
translated by 谷歌翻译
Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing studies visually analyze the mechanisms of convolutional neural networks, an analogous exploration of ViTs remains challenging. In this paper, we first address the obstacles to performing visualizations on ViTs. Assisted by these solutions, we observe that neurons in ViTs trained with language model supervision (e.g., CLIP) are activated by semantic concepts rather than visual features. We also explore the underlying differences between ViTs and CNNs, and we find that transformers detect image background features, just like their convolutional counterparts, but their predictions depend far less on high-frequency information. On the other hand, both architecture types behave similarly in the way features progress from abstract patterns in early layers to concrete objects in late layers. In addition, we show that ViTs maintain spatial information in all layers except the final layer. In contrast to previous works, we show that the last layer most likely discards the spatial information and behaves as a learned global pooling operation. Finally, we conduct large-scale visualizations on a wide range of ViT variants, including DeiT, CoaT, ConViT, PiT, Swin, and Twin, to validate the effectiveness of our method.
translated by 谷歌翻译
标准扩散模型涉及图像变换 - 添加高斯噪声 - 以及逆转此降解的图像恢复操作员。我们观察到,扩散模型的生成行为并不是很大程度上取决于图像降解的选择,实际上,可以通过改变这种选择来构建整个生成模型家族。即使使用完全确定性的降解(例如,模糊,掩蔽等),培训和测试时间更新规则是基于扩散模型的培训和测试时间更新规则,可以轻松地概括为创建生成模型。这些完全确定的模型的成功使社区对扩散模型的理解质疑,这依赖于梯度Langevin动力学或变异推理中的噪声,并为反转任意过程的广义扩散模型铺平了道路。我们的代码可从https://github.com/arpitbansal297/cold-diffusion-models获得
translated by 谷歌翻译
步行运动计划基于运动的不同组成部分(DCM)和线性倒置模型(LIPM)是可以实现的替代方案之一,以生成在线人类人体机器人步态轨迹。该算法需要调整不同的参数。在此,我们开发了一个框架来获得最佳参数,以实现Real Robot步态的稳定且节能的轨迹。为了找到最佳轨迹,在机器人的每个下肢关节下,代表能耗的四个成本函数,关节速度和应用扭矩的总和,以及基于零矩(ZMP)稳定性标准的成本函数。遗传算法用于框架中,以优化这些成本函数中的每一个。尽管轨迹计划是在简化模型的帮助下完成的,但通过考虑Bullet Physics Engine Simulator中的完整动力学模型和脚部接触模型,可以获得每个成本函数的值。这种优化的结果是,以最有效的方式行走的最稳定性和行走是相互对比的。因此,在另一次尝试中,对ZMP和以三种不同速度的能量成本函数进行了多目标优化。最后,我们比较了使用最佳参数生成的设计轨迹,并将模拟产生的仿真模拟器。
translated by 谷歌翻译
完全监督分类的问题是,它需要大量的注释数据,但是,在许多数据集中,很大一部分数据是未标记的。为了缓解此问题,半监督学习(SSL)利用了标记域上的分类器知识,并将其推送到无标记的域,该域具有与注释数据相似的分布。 SSL方法的最新成功至关重要地取决于阈值伪标记,从而对未标记的域的一致性正则化。但是,现有方法并未在训练过程中纳入伪标签或未标记样品的不确定性,这是由于嘈杂的标签或由于强大的增强而导致的分布样品。受SSL最近发展的启发,我们本文的目标是提出一个新颖的无监督不确定性意识的目标,依赖于核心和认识论不确定性量化。通过提出的不确定性感知损失功能,我们的方法优于标准SSL基准,在计算轻量级的同时,与最新的方法相匹配,或与最先进的方法相提并论。我们的结果优于复杂数据集(例如CIFAR-100和MINI-IMAGENET)的最新结果。
translated by 谷歌翻译
我们检查了通过直播(OTA)聚合的联合学习(FL),移动用户(MUS)旨在借助聚合本地梯度的参数服务器(PS)在全球模型上达成共识。在OTA FL中,MUS在每个训练回合中使用本地数据训练他们的模型,并以未编码的方式使用相同的频带同时传输其梯度。根据超级梯度的接收信号,PS执行全局模型更新。尽管OTA FL的通信成本显着降低,但它容易受到不利的通道影响和噪声的影响。在接收器侧采用多个天线可以减少这些效果,但是对于远离PS的用户来说,路径损失仍然是一个限制因素。为了改善此问题,在本文中,我们提出了一种基于无线的层次FL方案,该方案使用中间服务器(ISS)在MUS更密集的区域形成簇。我们的计划利用OTA群集聚合与MUS与其相应的IS进行交流,而OTA全球聚合从ISS到PS。我们提出了针对所提出算法的收敛分析,并通过对使用ISS的衍生分析表达式和实验结果的数值评估显示,与单独使用较少的传输功率相比,利用ISS的结果比单独的OTA FL具有更快的收敛性和更好的性能。我们还使用不同数量的群集迭代以及不同数据集和数据分布来验证性能的结果。我们得出的结论是,群集聚集的最佳选择取决于MUS和集群之间的数据分布。
translated by 谷歌翻译
经验重播是深入增强学习(DRL)的重要组成部分,它可以存储经验并为代理商实时学习的经验。最近,优先的经验重播(PER)已被证明是强大的,并且在DRL代理中已广泛部署。但是,由于其频繁和不规则的内存访问,在传统的CPU或GPU架构上实施会造成大量的延迟开销。本文提出了一种硬件软件共同设计方法,以设计基于AMPER的相关内存(AM),并具有AM友好的优先采样操作。 Amper在保留学习绩效的同时,以PER中的Per取代了广泛使用的时间成本的基于Tree-Traversal的优先级抽样。此外,我们设计了基于AM的内存计算硬件体系结构,以通过利用并行的内存搜索操作来支持安珀。与GPU上的每次运行相比,Amper在在拟议的硬件上运行时,在拟议的硬件上运行55倍至270倍的延迟延迟时,显示出可比的学习表现。
translated by 谷歌翻译