In the field of locomotion task of quadruped robots, Blind Policy and Perceptive Policy each have their own advantages and limitations. The Blind Policy relies on preset sensor information and algorithms, suitable for known and structured environments, but it lacks adaptability in complex or unknown environments. The Perceptive Policy uses visual sensors to obtain detailed environmental information, allowing it to adapt to complex terrains, but its effectiveness is limited under occluded conditions, especially when perception fails. Unlike the Blind Policy, the Perceptive Policy is not as robust under these conditions. To address these challenges, we propose a MBC:Multi-Brain collaborative system that incorporates the concepts of Multi-Agent Reinforcement Learning and introduces collaboration between the Blind Policy and the Perceptive Policy. By applying this multi-policy collaborative model to a quadruped robot, the robot can maintain stable locomotion even when the perceptual system is impaired or observational data is incomplete. Our simulations and real-world experiments demonstrate that this system significantly improves the robot's passability and robustness against perception failures in complex environments, validating the effectiveness of multi-policy collaboration in enhancing robotic motion performance.
相關內容
Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. A combined fusion of target mask generation and style transfer units, with a cascaded self-attention mechanism has been proposed to focus on multi-level text region edits to handle varying word lengths. Extensive evaluation on a real-world database with further subjective human evaluation study indicates the superiority of FASTER in both scene text editing and rendering tasks, in terms of model performance and efficiency. Our code will be released upon acceptance.
We introduce AmbigNLG, a novel task designed to tackle the challenge of task ambiguity in instructions for Natural Language Generation (NLG). Ambiguous instructions often impede the performance of Large Language Models (LLMs), especially in complex NLG tasks. To tackle this issue, we propose an ambiguity taxonomy that categorizes different types of instruction ambiguities and refines initial instructions with clearer specifications. Accompanying this task, we present AmbigSNI-NLG, a dataset comprising 2,500 instances annotated to facilitate research in AmbigNLG. Through comprehensive experiments with state-of-the-art LLMs, we demonstrate that our method significantly enhances the alignment of generated text with user expectations, achieving up to a 15.02-point increase in ROUGE scores. Our findings highlight the critical importance of addressing task ambiguity to fully harness the capabilities of LLMs in NLG tasks. Furthermore, we confirm the effectiveness of our method in practical settings involving interactive ambiguity mitigation with users, underscoring the benefits of leveraging LLMs for interactive clarification.
We introduce EMMA, an End-to-end Multimodal Model for Autonomous driving. Built on a multi-modal large language model foundation, EMMA directly maps raw camera sensor data into various driving-specific outputs, including planner trajectories, perception objects, and road graph elements. EMMA maximizes the utility of world knowledge from the pre-trained large language models, by representing all non-sensor inputs (e.g. navigation instructions and ego vehicle status) and outputs (e.g. trajectories and 3D locations) as natural language text. This approach allows EMMA to jointly process various driving tasks in a unified language space, and generate the outputs for each task using task-specific prompts. Empirically, we demonstrate EMMA's effectiveness by achieving state-of-the-art performance in motion planning on nuScenes as well as competitive results on the Waymo Open Motion Dataset (WOMD). EMMA also yields competitive results for camera-primary 3D object detection on the Waymo Open Dataset (WOD). We show that co-training EMMA with planner trajectories, object detection, and road graph tasks yields improvements across all three domains, highlighting EMMA's potential as a generalist model for autonomous driving applications. However, EMMA also exhibits certain limitations: it can process only a small amount of image frames, does not incorporate accurate 3D sensing modalities like LiDAR or radar and is computationally expensive. We hope that our results will inspire further research to mitigate these issues and to further evolve the state of the art in autonomous driving model architectures.
Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 30 countries on four continents, covering 31 languages with 13 scripts, providing a total of 10k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field.
In the era of the Internet of Things (IoT) and data sharing, users frequently upload their personal information to enterprise databases to enjoy enhanced service experiences provided by various online services. However, the widespread presence of system vulnerabilities, remote network intrusions, and insider threats significantly increases the exposure of private enterprise data on the internet. If such data is stolen or leaked by attackers, it can result in severe asset losses and business operation disruptions. To address these challenges, this paper proposes a novel threat detection framework, TabITD. This framework integrates Intrusion Detection Systems (IDS) with User and Entity Behavior Analytics (UEBA) strategies to form a collaborative detection system that bridges the gaps in existing systems' capabilities. It effectively addresses the blurred boundaries between external and insider threats caused by the diversification of attack methods, thereby enhancing the model's learning ability and overall detection performance. Moreover, the proposed method leverages the TabNet architecture, which employs a sparse attention feature selection mechanism that allows TabNet to select the most relevant features at each decision step, thereby improving the detection of rare-class attacks. We evaluated our proposed solution on two different datasets, achieving average accuracies of 96.71% and 97.25%, respectively. The results demonstrate that this approach can effectively detect malicious behaviors such as masquerade attacks and external threats, significantly enhancing network security defenses and the efficiency of network attack detection.
The traditional visual-inertial SLAM system often struggles with stability under low-light or motion-blur conditions, leading to potential lost of trajectory tracking. High accuracy and robustness are essential for the long-term and stable localization capabilities of SLAM systems. Addressing the challenges of enhancing robustness and accuracy in visual-inertial SLAM, this paper propose SuperVINS, a real-time visual-inertial SLAM framework designed for challenging imaging conditions. In contrast to geometric modeling, deep learning features are capable of fully leveraging the implicit information present in images, which is often not captured by geometric features. Therefore, SuperVINS, developed as an enhancement of VINS-Fusion, integrates the deep learning neural network model SuperPoint for feature point extraction and loop closure detection. At the same time, a deep learning neural network LightGlue model for associating feature points is integrated in front-end feature matching. A feature matching enhancement strategy based on the RANSAC algorithm is proposed. The system is allowed to set different masks and RANSAC thresholds for various environments, thereby balancing computational cost and localization accuracy. Additionally, it allows for flexible training of specific SuperPoint bag of words tailored for loop closure detection in particular environments. The system enables real-time localization and mapping. Experimental validation on the well-known EuRoC dataset demonstrates that SuperVINS is comparable to other visual-inertial SLAM system in accuracy and robustness across the most challenging sequences. This paper analyzes the advantages of SuperVINS in terms of accuracy, real-time performance, and robustness. To facilitate knowledge exchange within the field, we have made the code for this paper publicly available.
Noisy Intermediate-Scale Quantum (NISQ) computers face a critical limitation in qubit numbers, hindering their progression towards large-scale and fault-tolerant quantum computing. A significant challenge impeding scaling is crosstalk, characterized by unwanted interactions among neighboring components on quantum chips, including qubits, resonators, and substrate. We motivate a general approach to systematically resolving multifaceted crosstalks in a limited substrate area. We propose Qplacer, a frequency-aware electrostatic-based placement framework tailored for superconducting quantum computers, to alleviate crosstalk by isolating these components in spatial and frequency domains alongside compact substrate design. Qplacer commences with a frequency assigner that ensures frequency domain isolation for qubits and resonators. It then incorporates a padding strategy and resonator partitioning for layout flexibility. Central to our approach is the conceptualization of quantum components as charged particles, enabling strategic spatial isolation through a 'frequency repulsive force' concept. Our results demonstrate that Qplacer carefully crafts the physical component layout in mitigating various crosstalk impacts while maintaining a compact substrate size. On various device topologies and NISQ benchmarks, Qplacer improves fidelity by an average of 36.7x and reduces spatial violations (susceptible to crosstalk) by an average of 12.76x, compared to classical placement engines. Regarding area optimization, compared to manual designs, Qplacer can reduce the required layout area by 2.14x on average
Drones have revolutionized the fields of aerial imaging, mapping, and disaster recovery. However, the deployment of drones in low-light conditions is constrained by the image quality produced by their on-board cameras. In this paper, we present a learning architecture for improving 3D reconstructions in low-light conditions by finding features in a burst. Our approach enhances visual reconstruction by detecting and describing high quality true features and less spurious features in low signal-to-noise ratio images. We demonstrate that our method is capable of handling challenging scenes in millilux illumination, making it a significant step towards drones operating at night and in extremely low-light applications such as underground mining and search and rescue operations.
This paper presents SCALER, a versatile free-climbing multi-limbed robot that is designed to achieve tightly coupled simultaneous locomotion and dexterous grasping. Although existing quadruped-limbed robots have shown impressive dexterous skills such as object manipulation, it is essential to balance power-intensive locomotion and dexterous grasping capabilities. We design a torso linkage and a parallel-serial limb to meet such conflicting skills that pose unique challenges in the hardware designs. SCALER employs underactuated two-fingered GOAT grippers that can mechanically adapt and offer 7 modes of grasping, enabling SCALER to traverse extreme terrains with multi-modal grasping strategies. We study the whole-body approach, where SCALER uses its body and limbs to generate additional forces for stable grasping with environments, further enhancing versatility. Furthermore, we improve the GOAT gripper actuation speed to realize more dynamic climbing in a closed-loop control fashion. With these proposed technologies, SCALER can traverse vertical, overhang, upside-down, slippery terrains, and bouldering walls with non-convex-shaped climbing holds under the Earth's gravity.
Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness. In this work, we propose to use pre-trained language models for knowledge graph completion. We treat triples in knowledge graphs as textual sequences and propose a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples. Our method takes entity and relation descriptions of a triple as input and computes scoring function of the triple with the KG-BERT language model. Experimental results on multiple benchmark knowledge graphs show that our method can achieve state-of-the-art performance in triple classification, link prediction and relation prediction tasks.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191