A reliable pose estimator robust to environmental disturbances is desirable for mobile robots. To this end, inertial measurement units (IMUs) play an important role because they can perceive the full motion state of the vehicle independently. However, it suffers from accumulative error due to inherent noise and bias instability, especially for low-cost sensors. In our previous studies on Wheel-INS \cite{niu2021, wu2021}, we proposed to limit the error drift of the pure inertial navigation system (INS) by mounting an IMU to the wheel of the robot to take advantage of rotation modulation. However, it still drifted over a long period of time due to the lack of external correction signals. In this letter, we propose to exploit the environmental perception ability of Wheel-INS to achieve simultaneous localization and mapping (SLAM) with only one IMU. To be specific, we use the road bank angles (mirrored by the robot roll angles estimated by Wheel-INS) as terrain features to enable the loop closure with a Rao-Blackwellized particle filter. The road bank angle is sampled and stored according to the robot position in the grid maps maintained by the particles. The weights of the particles are updated according to the difference between the currently estimated roll sequence and the terrain map. Field experiments suggest the feasibility of the idea to perform SLAM in Wheel-INS using the robot roll angle estimates. In addition, the positioning accuracy is improved significantly (more than 30\%) over Wheel-INS. Source code of our implementation is publicly available (https://github.com/i2Nav-WHU/Wheel-SLAM).

A reliable self-contained navigation system is essential for autonomous vehicles. Based on our previous study on Wheel-INS \cite{niu2019}, a wheel-mounted inertial measurement unit (Wheel-IMU)-based dead reckoning (DR) system, in this paper, we propose a multiple IMUs-based DR solution for the wheeled robots. The IMUs are mounted at different places of the wheeled vehicles to acquire various dynamic information. In particular, at least one IMU has to be mounted at the wheel to measure the wheel velocity and take advantages of the rotation modulation. The system is implemented through a distributed extended Kalman filter structure where each subsystem (corresponding to each IMU) retains and updates its own states separately. The relative position constraints between the multiple IMUs are exploited to further limit the error drift and improve the system robustness. Particularly, we present the DR systems using dual Wheel-IMUs, one Wheel-IMU plus one vehicle body-mounted IMU (Body-IMU), and dual Wheel-IMUs plus one Body-IMU as examples for analysis and comparison. Field tests illustrate that the proposed multi-IMU DR system outperforms the single Wheel-INS in terms of both positioning and heading accuracy. By comparing with the centralized filter, the proposed distributed filter shows unimportant accuracy degradation while holds significant computation efficiency. Moreover, among the three multi-IMU configurations, the one Body-IMU plus one Wheel-IMU design obtains the minimum drift rate. The position drift rates of the three configurations are 0.82\% (dual Wheel-IMUs), 0.69\% (one Body-IMU plus one Wheel-IMU), and 0.73\% (dual Wheel-IMUs plus one Body-IMU), respectively.

In this paper, we present the Circular Accessible Depth (CAD), a robust traversability representation for an unmanned ground vehicle (UGV) to learn traversability in various scenarios containing irregular obstacles. To predict CAD, we propose a neural network, namely CADNet, with an attention-based multi-frame point cloud fusion module, Stability-Attention Module (SAM), to encode the spatial features from point clouds captured by LiDAR. CAD is designed based on the polar coordinate system and focuses on predicting the border of traversable area. Since it encodes the spatial information of the surrounding environment, which enables a semi-supervised learning for the CADNet, and thus desirably avoids annotating a large amount of data. Extensive experiments demonstrate that CAD outperforms baselines in terms of robustness and precision. We also implement our method on a real UGV and show that it performs well in real-world scenarios.

Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information. Recent studies show that current models rely on shallow heuristics to predict solutions and could be easily misled by small textual perturbations. To address this problem, we propose a Textual Enhanced Contrastive Learning framework, which enforces the models to distinguish semantically similar examples while holding different mathematical logic. We adopt a self-supervised manner strategy to enrich examples with subtle textual variance by textual reordering or problem re-construction. We then retrieve the hardest to differentiate samples from both equation and textual perspectives and guide the model to learn their representations. Experimental results show that our method achieves state-of-the-art on both widely used benchmark datasets and also exquisitely designed challenge datasets in English and Chinese. \footnote{Our code and data is available at \url{https://github.com/yiyunya/Textual_CL_MWP}

While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that uncurated robot demonstration data, i.e. play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal. This makes extracting useful, task-centric behaviors from such data a difficult generative modeling problem. In this work, we present Conditional Behavior Transformers (C-BeT), a method that combines the multi-modal generation ability of Behavior Transformer with future-conditioned goal specification. On a suite of simulated benchmark tasks, we find that C-BeT improves upon prior state-of-the-art work in learning from play data by an average of 45.7%. Further, we demonstrate for the first time that useful task-centric behaviors can be learned on a real-world robot purely from play data without any task labels or reward information. Robot videos are best viewed on our project website: https://play-to-policy.github.io

为了解决数学单词问题，人类学生利用达到不同方程解决方案的各种推理逻辑。但是，自动求解器的主流序列到序列方法旨在解码通过人类注释监督的固定溶液方程。在本文中，我们通过利用一组控制代码来指导模型考虑某些推理逻辑并解码从人类参考转换的相应方程式表达式来指导模型来考虑某些推理逻辑并解码相应的方程式表达式来提出一个受控方程生成求解器。经验结果表明，我们的方法普遍提高了单人（MATH23K）和多项（draw1k，hmwp）基准的性能，在具有挑战性的多重未知数据集上，高达13.2％的准确性。

在本文中，我们开发了一种新的多弦乐中国神经唱歌声音合成（SVS）系统，名为Wesinger。为了提高合成声音的准确性和自然性，我们设计了几个特定的​​模块和技术：1）具有多尺度节奏损失和后处理步骤的深度双向LSTM的持续时间模型； 2）类似变压器的声学模型，具有渐进的俯仰加权解码器损失； 3）24 kHz音调感知的LPCNET神经声码器可产生高质量的唱歌波形； 4）一种新型的数据增强方法，具有多手柄预训练，以实现更强的鲁棒性和自然性。据我们所知，Wesinger是第一个同时采用24 kHz LPCNET和多手指预训练的SVS系统。定量和定性评估结果都证明了Wesinger在准确性和自然方面的有效性，并且Wesinger在最近的中国公共唱歌语料库Opencpop \ footNote上实现了最先进的表现{https://wenet.org.cn/ OPENCPOP/}。一些合成的歌曲样本在线可用\ footNote {https://zzw922cn.github.io/wesinger/}。

用于头部和颈鳞状细胞癌（HNSCC）的诊断和治疗管理由常规诊断头和颈部计算断层扫描（CT）扫描引导，以识别肿瘤和淋巴结特征。折叠延伸（ECE）是患者的患者生存结果与HNSCC的强烈预测因子。在改变患者的暂存和管理时，必须检测ECE的发生至关重要。目前临床ECE检测依赖于放射科学医生进行的视觉鉴定和病理确认。基于机器学习（ML）的ECE诊断在近年来的潜力上表现出很高的潜力。然而，在大多数基于ML的ECE诊断研究中，手动注释是淋巴结区域的必要数据预处理步骤。此外，本手册注释过程是耗时，劳动密集型和容易出错。因此，在本文中，我们提出了一种梯度映射引导的可解释网络（GMGenet）框架，以自动执行ECE识别而不需要注释的淋巴结区域信息。提出了梯度加权类激活映射（GRAC-CAM）技术，以指导深度学习算法专注于与ECE高度相关的区域。提取信息丰富的兴趣（VoIS），无需标记淋巴结区域信息。在评估中，所提出的方法是使用交叉验证的训练和测试，可分别实现测试精度和90.2％和91.1％的AUC。已经分析了ECE的存在或不存在并与黄金标准组织病理学发现相关。

在该研究中，提出了一种具有贝叶斯优化（ADSNN-BO）的关注深度可分离的神经网络，以检测和分类稻米图像的水稻疾病。水稻疾病经常导致20至40％的公司生产损失的产量，与全球经济有关。快速疾病鉴定对于计划及时计划治疗并减​​少CORP损失至关重要。水稻疾病诊断仍然主要是手动进行的。为实现AI辅助快速准确的疾病检测，我们提出了基于MobileNet结构的Adsnn-Bo模型和增强注意机制。此外，贝叶斯优化方法应用于调整模型的超级参数。交叉验证的分类实验是基于公共米病数据集进行的，总共有四个类别。实验结果表明，我们的移动兼容ADSNN-BO模型实现了94.65 \％的测试精度，这占据了所有最先进的模型。为了检查我们所提出的模型的可解释性，还进行了包括激活图和过滤器可视化方法的特征分析。结果表明，我们提出的基于关注机制可以更有效地引导Adsnn-Bo模型学习信息性功能。本研究的结果将促进农业领域快速植物疾病诊断和控制的人工智能。

促销活动在电子商务平台上变得更加重要和普遍，以吸引客户和提升销售。但是，推荐系统中的点击率（CTR）预测方法无法处理此类情况，因为：1）他们无法概括为服务，因为在线数据分布是不确定的，因为可能正在推出的促销潜在的促销; 2）在不够重视方案信号的情况下，它们无法学习在每个场景中共存的不同特征表示模式。在这项工作中，我们提出了方案自适应混合的专家（相同），这是一个简单而有效的模型，用于促销和正常情况。从技术上讲，它通过采用多个专家来学习专家来遵循专家混合的想法，这些特征表示通过注意机制通过特征门控网络（FGN）进行调制。为了获得高质量的表示，我们设计了一个堆叠的并行关注单元（SPAU），以帮助每个专家更好地处理用户行为序列。为了解决分布不确定性，从时间序列预测的角度精确地设计了一组场景信号，并馈入FGN，其输出与来自每个专家的特征表示连接，以学会注意。因此，特征表示的混合是自适应的场景和用于最终的CTR预测。通过这种方式，每个专家都可以学习鉴别的表示模式。据我们所知，这是第一次推广感知CTR预测的研究。实验结果对现实世界数据集验证了同一的优势。在线A / B测试也表现出同样的促销期间在CTR上的显着增益和5.94％的IPV，分别在正常日内为3.93％和6.57％。