We study algorithms for detecting and including glass objects in an optimization-based Simultaneous Localization and Mapping (SLAM) algorithm in this work. When LiDAR data is the primary exteroceptive sensory input, glass objects are not correctly registered. This occurs as the incident light primarily passes through the glass objects or reflects away from the source, resulting in inaccurate range measurements for glass surfaces. Consequently, the localization and mapping performance is impacted, thereby rendering navigation in such environments unreliable. Optimization-based SLAM solutions, which are also referred to as Graph SLAM, are widely regarded as state of the art. In this paper, we utilize a simple and computationally inexpensive glass detection scheme for detecting glass objects and present the methodology to incorporate the identified objects into the occupancy grid maintained by such an algorithm (Google Cartographer). We develop both local (submap level) and global algorithms for achieving the objective mentioned above and compare the maps produced by our method with those produced by an existing algorithm that utilizes particle filter based SLAM.

Force modulation of robotic manipulators has been extensively studied for several decades. However, it is not yet commonly used in safety-critical applications due to a lack of accurate interaction contact modeling and weak performance guarantees - a large proportion of them concerning the modulation of interaction forces. This study presents a high-level framework for simultaneous trajectory optimization and force control of the interaction between a manipulator and soft environments, which is prone to external disturbances. Sliding friction and normal contact force are taken into account. The dynamics of the soft contact model and the manipulator are simultaneously incorporated in a trajectory optimizer to generate desired motion and force profiles. A constrained optimization framework based on Alternative Direction Method of Multipliers (ADMM) has been employed to efficiently generate real-time optimal control inputs and high-dimensional state trajectories in a Model Predictive Control fashion. Experimental validation of the model performance is conducted on a soft substrate with known material properties using a Cartesian space force control mode. Results show a comparison of ground truth and real-time model-based contact force and motion tracking for multiple Cartesian motions in the valid range of the friction model. It is shown that a contact model-based motion planner can compensate for frictional forces and motion disturbances and improve the overall motion and force tracking accuracy. The proposed high-level planner has the potential to facilitate the automation of medical tasks involving the manipulation of compliant, delicate, and deformable tissues.

The widespread of offensive content online, such as hate speech and cyber-bullying, is a global phenomenon. This has sparked interest in the artificial intelligence (AI) and natural language processing (NLP) communities, motivating the development of various systems trained to detect potentially harmful content automatically. These systems require annotated datasets to train the machine learning (ML) models. However, with a few notable exceptions, most datasets on this topic have dealt with English and a few other high-resource languages. As a result, the research in offensive language identification has been limited to these languages. This paper addresses this gap by tackling offensive language identification in Sinhala, a low-resource Indo-Aryan language spoken by over 17 million people in Sri Lanka. We introduce the Sinhala Offensive Language Dataset (SOLD) and present multiple experiments on this dataset. SOLD is a manually annotated dataset containing 10,000 posts from Twitter annotated as offensive and not offensive at both sentence-level and token-level, improving the explainability of the ML models. SOLD is the first large publicly available offensive language dataset compiled for Sinhala. We also introduce SemiSOLD, a larger dataset containing more than 145,000 Sinhala tweets, annotated following a semi-supervised approach.

我们提出了一种新颖的轨迹遍历性估计和计划在复杂室外环境中机器人导航的算法。我们将RGB摄像头，3D LIDAR和机器人的探针传感器中的多模式感觉输入结合在一起，以训练预测模型，以估算基于部分可靠的多模式传感器观测值的候选轨迹轨迹的成功概率。我们使用编码器网络对低维特征向量编码高维多模式的感觉输入，并将它们表示为连接的图形，以训练基于注意力的图形神经网络（GNN）模型，以预测轨迹成功概率。我们进一步分别分析图像和点云数据，以量化传感器的可靠性，以增强我们GNN中使用的特征图表示的权重。在运行时，我们的模型利用多传感器输入来预测本地规划师生成的轨迹的成功概率，以避免潜在的碰撞和故障。当一个或多个传感器模态在复杂的室外环境中不可靠或不可用时，我们的算法证明了可靠的预测。我们使用现实世界中户外环境中的点机器人评估算法的导航性能。

我们提出了一种新的方法，以改善基于深入强化学习（DRL）的室外机器人导航系统的性能。大多数现有的DRL方法基于精心设计的密集奖励功能，这些功能可以学习环境中的有效行为。我们仅通过稀疏的奖励（易于设计）来解决这个问题，并提出了一种新颖的自适应重尾增强算法，用于户外导航，称为Htron。我们的主要思想是利用重尾政策参数化，这些参数隐含在稀疏的奖励环境中引起探索。我们在三种不同的室外场景中评估了针对钢琴，PPO和TRPO算法的htron的性能：进球，避免障碍和地形导航不均匀。我们平均观察到成功率的平均增加了34.41％，与其他方法相比，与其他方法获得的导航政策相比，为达到目标的平均时间步骤下降了15.15％，高程成本下降了24.9％。此外，我们证明我们的算法可以直接转移到Clearpath Husky机器人中，以在现实情况下进行户外地形导航。

我们提出了一种新颖的户外导航算法，以生成稳定，有效的动作，以将机器人导航到目标。我们使用多阶段的训练管道，并表明我们的模型产生了政策，从而在复杂的地形上导致稳定且可靠的机器人导航。基于近端政策优化（PPO）算法，我们开发了一种新颖的方法来实现户外导航任务的多种功能，即：减轻机器人的漂移，使机器人在颠簸的地形上保持稳定，避免在山丘上攀登，并具有陡峭的山坡，并改变了山坡，并保持了陡峭的高度变化，并使机器人稳定在山坡上，并避免了攀岩地面上的攀登，并避免了机器人的攀岩地形，并避免了机器人的攀岩地形。避免碰撞。我们的培训过程通过引入更广泛的环境和机器人参数以及统一模拟器中LIDAR感知的丰富特征来减轻现实（SIM到现实）差距。我们使用Clearphith Husky和Jackal在模拟和现实世界中评估我们的方法。此外，我们将我们的方法与最先进的方法进行了比较，并表明在现实世界中，它在不平坦的地形上至少提高了30.7％通过防止机器人在高梯度的区域移动，机器人在每个运动步骤处的高程变化。

我们提出了Terrapn，这是一种新颖的方法，它可以通过自我监督的学习直接从机器人 - 泰林相互作用中了解复杂室外地形的表面特性（牵引力，颠簸，可变形等），并将其用于自动驾驶机器人导航。我们的方法使用地形表面和机器人的速度的RGB图像作为输入，以及机器人作为自我选择的标签所经历的IMU振动和探测错误。我们的方法计算了一个表面成本图，该图将平滑，高吸收表面（低导航成本）与颠簸，滑水，可变形表面（高导航成本）区分开。我们通过检测表面之间的边界来计算从输入RGB图像的非均匀采样贴片来计算成本图，从而与均匀的采样和现有分割方法相比，导致推理时间较低（低47.27％）。我们提出了一种新颖的导航算法，该算法可以说明表面成本，计算机器人的基于成本的加速度限制以及动态可行的无碰撞轨迹。 Terrapn的表面成本预测可以在约25分钟内进行五个不同的表面进行训练，而先前基于学习的分割方法数小时。在导航方面，我们的方法在成功率（高达35.84％），轨迹的振动成本（降低21.52％）方面优于先前的工作，并在颠簸，可变形的表面上放慢机器人（最高46.76％）在不同的情况下较慢）。

深度学习（DL）模型为各种医学成像基准挑战提供了最先进的性能，包括脑肿瘤细分（BRATS）挑战。然而，局灶性病理多隔室分割（例如，肿瘤和病变子区）的任务特别具有挑战性，并且潜在的错误阻碍DL模型转化为临床工作流程。量化不确定形式的DL模型预测的可靠性，可以实现最不确定的地区的临床审查，从而建立信任并铺平临床翻译。最近，已经引入了许多不确定性估计方法，用于DL医学图像分割任务。开发指标评估和比较不确定性措施的表现将有助于最终用户制定更明智的决策。在本研究中，我们探索并评估在Brats 2019-2020任务期间开发的公制，以对不确定量化量化（Qu-Brats），并旨在评估和排列脑肿瘤多隔室分割的不确定性估计。该公制（1）奖励不确定性估计，对正确断言产生高置信度，以及在不正确的断言处分配低置信水平的估计数，（2）惩罚导致更高百分比的无关正确断言百分比的不确定性措施。我们进一步基准测试由14个独立参与的Qu-Brats 2020的分割不确定性，所有这些都参与了主要的Brats细分任务。总体而言，我们的研究结果证实了不确定性估计提供了分割算法的重要性和互补价值，因此突出了医学图像分析中不确定性量化的需求。我们的评估代码在HTTPS://github.com/ragmeh11/qu-brats公开提供。

Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks. To avoid performance decrease caused by forgetting, prior studies exploit episodic memory (EM), which stores a subset of the past observed samples while learning from new non-i.i.d. data. Despite the promising results, since CL is often assumed to execute on mobile or IoT devices, the EM size is bounded by the small hardware memory capacity and makes it infeasible to meet the accuracy requirements for real-world applications. Specifically, all prior CL methods discard samples overflowed from the EM and can never retrieve them back for subsequent training steps, incurring loss of information that would exacerbate catastrophic forgetting. We explore a novel hierarchical EM management strategy to address the forgetting issue. In particular, in mobile and IoT devices, real-time data can be stored not just in high-speed RAMs but in internal storage devices as well, which offer significantly larger capacity than the RAMs. Based on this insight, we propose to exploit the abundant storage to preserve past experiences and alleviate the forgetting by allowing CL to efficiently migrate samples between memory and storage without being interfered by the slow access speed of the storage. We call it Carousel Memory (CarM). As CarM is complementary to existing CL methods, we conduct extensive evaluations of our method with seven popular CL methods and show that CarM significantly improves the accuracy of the methods across different settings by large margins in final average accuracy (up to 28.4%) while retaining the same training efficiency.

我们提出了GANAV，这是一种新颖的小组注意机制，可以从RGB图像中识别出越野地形和非结构化环境中的安全和可通道的区域。我们的方法根据其可通道的语义分割根据其可通道水平对地形进行了分类。我们新颖的小组注意力损失使任何骨干网络都能明确关注具有低空间分辨率的不同组的特征。与现有的SOTA方法相比，我们的设计可提供有效的推断，同时保持高度的准确性。我们对RUGD和Rellis-3D数据集的广泛评估表明，GANAV在RUGD上的改善对SOTA MIOU的改善增长了2.25-39.05％，Rellis-3d的RUGD提高了5.17-19.06％。我们与Ganav进行了深入的增强基于学习的导航算法的接口，并在现实世界中的非结构化地形中突出了其在导航方面的好处。我们将基于GANAV的导航算法与ClearPath Jackal和Husky Robots集成在一起，并观察到成功率增加了10％，在选择表面最佳的可通道性和4.6-13.9％的表面方面为2-47％在轨迹粗糙度中。此外，加纳夫将禁区的假阳性降低37.79％。代码，视频和完整的技术报告可在https://gamma.umd.edu/offroad/上找到。