Multi-sensor fusion provides a promising route to robust odometry in GNSS-denied environments. However, existing fusion frameworks often rely on vision or LiDAR as dominant modalities, making their feature representations vulnerable to adverse weather and weak scene structures. To address this, we propose Self-RIO, a self-supervised odometry that integrates 2D millimeter-wave radar and inertial measurement unit (IMU) signals. To the best of our knowledge, this is the first end-to-end self-supervised spinning radar-inertial odometry. Specifically, we design an efficient cross-attention-based multi-modal fusion module that integrates radar and IMU data, facilitating the fusion of more informative features for localization under challenging conditions. Furthermore, to address the sparsity and irregular spatial distribution inherent in radar signals, we introduce a spatial-enhanced sparse CNN-Transformer radar backbone that improves radar feature robustness. Extensive experiments on standard benchmarks confirm the superior robustness of Self-RIO across diverse challenging conditions. On the Oxford Radar RobotCar dataset, Self-RIO achieves up to 22.9% improvement in pose accuracy while reducing computational complexity by 63.1% relative to the existing advanced learning-based method GRAMME, highlighting its robustness under diverse weather and urban conditions. Moreover, consistent improvements on the RADIATE and Oxford Offroad Radar datasets underscore its effectiveness in handling adverse weather and unstructured terrains. Self-RIO also demonstrates strong generalization performance on the MulRan dataset.

Visual-Inertial Odometry (VIO) provides a robust localization solution for Simultaneous Localization and Mapping (SLAM) systems. Self-supervised VIO, a leading approach, has the advantage of not requiring extensive ground-truth labels. Regrettably, this method still poses challenges for robotic applications, particularly unmanned aerial vehicles (UAVs), due to its computational complexity arising from inadequate model designs. To address this bottleneck, we introduce BotVIO (where “Bot” refers to “robotics”), a Transformer-based self-supervised VIO model, offering an excellent solution to alleviate computational burdens for robotics. Our lightweight backbone combines shallow CNNs with spatial-temporal-enhanced Transformers to replace conventional architectures, while the minimalist cross-fusion module uses single-layer cross-attention to enhance multimodal interaction. Extensive experiments show that, during pose estimation, BotVIO achieves a remarkable 70.37% reduction in trainable parameters and a 74.85% decrease in inference speed, reaching up to 57.80 fps on an NVIDIA Jetson NX (10W&2CORE), while improving pose accuracy and robustness. For the benefit of the community, we make public the source code.11https://github.com/wenhuiwei-ustc/BotVIO

Not relying on ground-truth data for training, self-supervised semantic visual odometry (SVO) has recently gained considerable attention. Within self-supervised SVO, feature representation inconsistency between semantic/depth and pose tasks presents a significant challenge, as it may disrupt cross-task feature representations and lead to notable performance degradation. Regrettably, existing self-supervised SVO lacks an effective solution to address this obstacle, for either overlooking this issue or exploiting a too heavy architecture. In response to this challenge, we propose a groundbreaking solution within the Single-Stream architecture, known as Lite-SVO, which is a lightweight yet efficient multi-feature sharing architecture. Lite-SVO is designed to bolster self-supervised SVO, facilitating its adoption on edge devices without compromising accuracy and performance. The crucial innovation lies in the multi-feature sharing architecture, which fuses the semantic and depth maps as pose features, thus significantly reducing the model complexity and boosting the speed in edge devices. Built upon the novel feature sharing framework, Lite-SVO further optimizes the feature sharing representation to improve the performance. Specifically, a cross-feature sharing module alleviates the impact of object boundary in depth estimation, while a multi-feature sharing module focuses on extracting and fusing spatial features to enhance pose estimation. Experimental results demonstrate that our method is at least 84.46% faster than the state-of-the-art Single-Stream approaches, and excitingly, our method’s pose accuracy is about 79.83% higher than theirs.

As the Augmented Intelligence of Things (AIoT) advances within vehicle-road coordination systems, challenges related to road traffic data transmission and processing are being increasingly addressed. However, this progress also brings significant risks of privacy data leakage. Federated learning (FL), a distributed machine learning paradigm, effectively safeguards client data privacy by allowing multiple participants to collaboratively train models while keeping their data localized. Despite its benefits, FL faces challenges, such as model parameter leakage and Byzantine attacks. To tackle these issues, this article introduces an anonymous and efficient FL framework for vehicle-road coordination systems (AEFL), designed to ensure a secure and reliable vehicle data transmission process. This architecture incorporates a novel group pairing onion routing protocol, which leverages pairing cryptography principles for hierarchical data encryption. During the routing process, relay group nodes decrypt the corresponding layer, ensuring both data confidentiality and node anonymity. Additionally, a sampling method is proposed to accurately identify Byzantine vehicle nodes, enhancing the precision of FL aggregation without compromising overall model performance. Experimental results show that AEFL outperforms the classic TOR anonymous routing protocol, achieving a 100% message delivery rate more quickly. Under the same conditions, the anonymity of the source node and the destination node improves by 3.9% and 1.9%, respectively. When half of the nodes are compromised, path anonymity can be increased by 24.8%. Furthermore, our framework excels in FL aggregation efficiency, with a Byzantine adversary detection accuracy of up to 99%.

Self-supervised monocular visual odometry has a crucial advantage of not depending on labels and has shown significant performance in autonomous driving and robotics. However, recent methods suffer from limited feature representations as they depend on coarse semantic masks to handle dynamic objects, resulting in diminished accuracy in dynamic environments. In contrast to these coarse-grained methods, we present Fine-MVO, a novel self-supervised monocular visual odometry that aims to address dynamic objects using implicit fine-grained feature representations, thus achieving excellent accuracy and robustness in dynamic environments. First, Fine-MVO provides an efficient cross-feature augmentation module and a novel loss weight balance strategy to effectively leverage fine-grained features with implicit semantic information, leading to a great improvement in the depth estimation accuracy, especially on object boundaries in the scenes. Secondly, we design a novel pose-feature enhancement module and an effective two-stage training policy to empower the pose network to focus on robust static regions and temporal information, thereby enhancing the pose estimation performance in dynamic and long-term environments. Extensive experimental results demonstrate the excellent accuracy and generalization of Fine-MVO. Specifically, Fine-MVO achieves a remarkable 36.80% improvement in pose accuracy over the state-of-the-art method on the KITTI dataset, which even breaks through the performance of loop closure within geometry-based visual odometry methods. Furthermore, Fine-MVO exhibits satisfactory generalization on the outdoor dataset AirDOS-Shibuya, attaining a notable improvement of 28.22% over current advanced method. Excitingly, Fine-MVO also reveals outstanding generalization on the indoor dataset TUM-RGBD.

For current traffic datasets, data scarcity is common in many districts. This limits the performance of existing spatial-temporal models. Current works tackle this problem by transferring knowledge from other cities. They mainly focus on grid-like data, thus not sharing graph structure information across cities. However, for graph-structured data like highway traffic flow, the spatial dependency between nodes is much more obvious. Furthermore, existing research focuses solely on data inconsistency between cities, ignoring data inconsistency in different periods. Towards these, we propose STG-Meta, a meta-learning-based framework for graph-based traffic prediction tasks with only limited training samples. Specifically, STG-Meta adopts the cross-city-cross-period task construction method to reflect the variation in data across periods. STG-Meta includes the structure memory to store the embedding of the structure patterns. Additionally, the optimization-based meta-learning method is utilized to extract knowledge such as the memory and the initialization parameters of spatial-temporal graph (STG) networks, from other cities. Experiments on realworld datasets of two traffic data types demonstrate that our method outperforms state-of-the-art approaches for data-scarce cities.

With the outbreak of COVID-19, how to mitigate and suppress its spread is a big issue to the government. Department of public health need powerful models to analyze and predict the trend and scale of such pandemic. And models that could evaluate the effect of the public policy are also essential to the fight with COVID-19. A main limitation of existing models is that they can only evaluate the policy by calculating R0after infection happens instead of giving observable index. To tackle this, based on the transmission characteristics of the COVID-19, we propose a novel framework Spatial-Temporal-Susceptible-Infected-Removed (STSIR) model. In particular, we combine both intra-city and inter-city mobility indices with the traditional SIR dynamics and make it a dynamic system. And we prove that the STSIR system is a closed system which makes the system self-consistent. And finally we proposed a Multi-Stage Simulated Annealing (MSSA) algorithm to find the optimal parameters of the system. In our experiments, based on Baidu Mobility dataset [1], and China pandemic dataset provided by Dingxiangyuan [2], our model can effectively predict the total scale of the pandemic and also give clear policy analysis with the observable index.

In this paper we share our solution to the Biomedia ACM MM Grand Challenge 2019, which focuses on the gastrointestinal tract with an aim to detect and classify abnormalities. We firstly identify the challenges in this task, including the scarce and imbalanced data, and the subtle inter-category variances. Based on these analysis, we propose a solution which leverages the 10-fold cross validation approach to alleviate the over-fitting problem, and design a model to adaptively ensemble all sub-models belonging to all component models. Based on extensive offline evaluations, we verify the performance of the proposed technique under various settings. In the competition, we eventually receive the MCC(Matthews correlation coefficient) score of 0.9480.