Underwater simulators offer support for building robust underwater perception solutions. Significant work has recently been done to develop new simulators and to advance the performance of existing underwater simulators. Still, there remains room for improvement on physics-based underwater sensor modeling and rendering efficiency. In this paper, we propose OceanSim, a high-fidelity GPU-accelerated underwater simulator to address this research gap. We propose advanced physics-based rendering techniques to reduce the sim-to-real gap for underwater image simulation. We develop OceanSim to fully leverage the computing advantages of GPUs and achieve real-time imaging sonar rendering and fast synthetic data generation. We evaluate the capabilities and realism of OceanSim using real-world data to provide qualitative and quantitative results. The code and detailed documentation are made available on the project website to support the marine robotics community: https://umfieldrobotics.github.io/OceanSim.

High-definition (HD) maps provide environmental information for autonomous driving systems and are essential for safe planning. While existing methods with single-frame input achieve impressive performance for online vector-ized HD map construction, they still struggle with complex scenarios and occlusions. We propose MemFusionMap, a novel temporal fusion model with enhanced temporal reasoning capabilities for online HD map construction. Specifically, we contribute a working memory fusion module that improves the model's memory capacity to reason across a history of frames. We also design a novel temporal over-lap heatmap to explicitly inform the model about the temporal overlap information and vehicle trajectory in the Bird's Eye View space. By integrating these two designs, MemFusionMap significantly outperforms existing methods while also maintaining a versatile design for scalability. We conduct extensive evaluation on open-source benchmarks and demonstrate a maximum improvement of 5.4% in mAP over state-of-the-art methods. The project page for MemFusion-Map is https://song-jingyu.github.io/MemFusionMap.

In the field of 3D object detection for autonomous driving, LiDAR-Camera (LC) fusion is the top-performing sensor configuration. Still, LiDAR is relatively high cost, which hinders adoption of this technology for consumer automobiles. Alternatively, camera and radar are commonly deployed on vehicles already on the road today, but performance of Camera-Radar (CR) fusion falls behind LC fusion. In this work, we propose Camera-Radar Knowledge Distillation (CRKD) to bridge the performance gap between LC and CR detectors with a novel cross-modality KD framework. We use the Bird'View (BEV) representation as the shared feature space to enable effective knowledge distillation. To accommodate the unique cross-modality KD path, we propose four distillation losses to help the student learn crucial features from the teacher model. We present extensive evaluations on the nuScenes dataset to demonstrate the effectiveness of the proposed CRKD framework. The project page for CRKD is https://song-jingyu.github.io/CRKD.

We propose LiRaFusion to tackle LiDAR-radar fusion for 3D object detection to fill the performance gap of existing LiDAR-radar detectors. To improve the feature extraction capabilities from these two modalities, we design an early fusion module for joint voxel feature encoding, and a middle fusion module to adaptively fuse feature maps via a gated network. We perform extensive evaluation on nuScenes to demonstrate that LiRaFusion leverages the complementary information of LiDAR and radar effectively and achieves notable improvement over existing methods.

Significant work has been done on advancing localization and mapping in underwater environments. Still, state-of-the-art methods are challenged by low-texture environments, which is common for underwater settings. This makes it difficult to use existing methods in diverse, real-world scenes. In this paper, we present TURTLMap, a novel solution that focuses on textureless underwater environments through a real-time localization and mapping method. We show that this method is low-cost, and capable of tracking the robot accurately, while constructing a dense map of a low-textured environment in real-time. We evaluate the proposed method using real-world data collected in an indoor water tank with a motion capture system and ground truth reference map. Qualitative and quantitative results validate the proposed system achieves accurate and robust localization and precise dense mapping, even when subject to wave conditions. The project page for TURTLMap is https://umfieldrobotics.github.io/TURTLMap.

Robotic perception is currently at a cross-roads between modern methods, which operate in an efficient latent space, and classical methods, which are mathematically founded and provide interpretable, trustworthy results. In this paper, we introduce a Convolutional Bayesian Kernel Inference (Con-vBKI) layer which learns to perform explicit Bayesian inference within a depthwise separable convolution layer to maximize efficency while maintaining reliability simultaneously. We apply our layer to the task of real-time 3D semantic mapping, where we learn semantic-geometric probability distributions for LiDAR sensor information and incorporate semantic predictions into a global map. We evaluate our network against state-of-the-art semantic mapping algorithms on the KITTI data set, demonstrating improved latency with comparable semantic label inference results.

Currently, the significance of a portal stems not only from being a handy way to access data but also from being the means of facilitating the integration with Web applications. This paper proposes an interaction instance oriented approach for integrating web applications in portals. The key aspect is to enable a user to have the same interaction experiences from a portal that he/she accesses the web application directly. The approach is thus focused on the description of the presentation layer of the interaction instances of a web application and a portlet, which defines an interaction instance as consecutive web pages or fragments. Web application integration is then transformed to the problem that how to translate all web pages of an interaction instance of a Web application to certain view equivalence regions, which form the interaction instance of a portlet. Experiments show that the approach is effective and efficient.

The paradigmatic shift from function-oriented Web services to interactive Web services(IWSs) addresses lots of issues such as repetitious development for user interface and tiresome understanding of underlying service operations. However, the composition of existing IWSs to create value-added ones is still a prominent problem. Considering the special interactive characteristics of IWSs, current approaches to compose function-oriented services are inappropriate. This paper proposes a novel user satisfaction model to evaluate the interactive quality of a composite IWS completely. Based on the satisfaction model, an effective satisfaction-driven approach is also developed for service selection in IWSs composition, which can meet diverse interactive requirements of users.

Traditional Web services are function oriented, where various developed standards mainly assist business applications to expose their functional descriptions, but each service consumer is required to develop different presentation logics for the same business logic respectively. Although works on the interactive Web service (IWS) make some progress and achieve the result of WSRP, researchers keep on making efforts to encapsulate user interface with the functional interface so as to present available information of content and facilitate the direct interactions between users and back-end services. Regarding IWS this paradigm of Web services, service selection shifts focus from function orientation to presentation orientation. This paper proposes a novel IWS description model with the extension of an element-view and its three sub-elements including presentation, content and interaction, with which IWS can be described more completely and accurately. Based on the description model, an IWS selection model with matching rules is developed, which can meet diverse selection requirements of service consumers at multiple levels and aspects