PyTorchKR Papers

최신 논문

총 2,097편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.19195

PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires the agent to follow language instructions to navigate through 3D environments. One main challenge in VLN is the limited availability of photorealistic training environments, which makes it hard to generalize to new and unseen environments. To address this problem, we propose PanoGen, a generation method that can potentially create an infinite number of diverse panoramic environments conditioned on text. Specifically, we collect room descriptions by captioning the room images in existing Matterport3D environments, and leverage a state-of-the-art text-to-image diffusion model to generate the new panoramic environments. We use recursive outpainting over the generated images to create consistent 360-degree panorama views. Our new panoramic environments share similar semantic information with the original environments by conditioning on text descriptions, which ensures the co-occurrence of objects in the panorama follows human intuition, and creates enough diversity in room appearance and layout with image outpainting. Lastly, we explore two ways of utilizing PanoGen in VLN pre-training and fine-tuning. We generate instructions for paths in our PanoGen environments with a speaker built on a pre-trained vision-and-language model for VLN pre-training, and augment the visual observation with our panoramic environments during agents' fine-tuning to avoid overfitting to seen environments. Empirically, learning with our PanoGen environments achieves the new state-of-the-art on the Room-to-Room, Room-for-Room, and CVDN datasets. Pre-training with our PanoGen speaker data is especially effective for CVDN, which has under-specified instructions and needs commonsense knowledge. Lastly, we show that the agent can benefit from training with more generated panoramic environments, suggesting promising results for scaling up the PanoGen environments.

arXiv:2305.17144공식 코드 · Papers with Code

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

The captivating realm of Minecraft has attracted substantial research interest in recent years, serving as a rich platform for developing intelligent agents capable of functioning in open-world environments. However, the current research landscape predominantly focuses on specific objectives, such as the popular "ObtainDiamond" task, and has not yet shown effective generalization to a broader spectrum of tasks. Furthermore, the current leading success rate for the "ObtainDiamond" task stands at around 20%, highlighting the limitations of Reinforcement Learning (RL) based controllers used in existing methods. To tackle these challenges, we introduce Ghost in the Minecraft (GITM), a novel framework integrates Large Language Models (LLMs) with text-based knowledge and memory, aiming to create Generally Capable Agents (GCAs) in Minecraft. These agents, equipped with the logic and common sense capabilities of LLMs, can skillfully navigate complex, sparse-reward environments with text-based interactions. We develop a set of structured actions and leverage LLMs to generate action plans for the agents to execute. The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate on the "ObtainDiamond" task, demonstrating superior robustness compared to traditional RL-based controllers. Notably, our agent is the first to procure all items in the Minecraft Overworld technology tree, demonstrating its extensive capabilities. GITM does not need any GPU for training, but a single CPU node with 32 CPU cores is enough. This research shows the potential of LLMs in developing capable agents for handling long-horizon, complex tasks and adapting to uncertainties in open-world environments. See the project website at https://github.com/OpenGVLab/GITM.

arXiv:2305.16925

How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers

Object goal navigation is an important problem in Embodied AI that involves guiding the agent to navigate to an instance of the object category in an unknown environment -- typically an indoor scene. Unfortunately, current state-of-the-art methods for this problem rely heavily on data-driven approaches, \eg, end-to-end reinforcement learning, imitation learning, and others. Moreover, such methods are typically costly to train and difficult to debug, leading to a lack of transferability and explainability. Inspired by recent successes in combining classical and learning methods, we present a modular and training-free solution, which embraces more classic approaches, to tackle the object goal navigation problem. Our method builds a structured scene representation based on the classic visual simultaneous localization and mapping (V-SLAM) framework. We then inject semantics into geometric-based frontier exploration to reason about promising areas to search for a goal object. Our structured scene representation comprises a 2D occupancy map, semantic point cloud, and spatial scene graph. Our method propagates semantics on the scene graphs based on language priors and scene statistics to introduce semantic knowledge to the geometric frontiers. With injected semantic priors, the agent can reason about the most promising frontier to explore. The proposed pipeline shows strong experimental performance for object goal navigation on the Gibson benchmark dataset, outperforming the previous state-of-the-art. We also perform comprehensive ablation studies to identify the current bottleneck in the object navigation task.

arXiv:2305.16818

Trust-Aware Resilient Control and Coordination of Connected and Automated Vehicles

We address the security of a network of Connected and Automated Vehicles (CAVs) cooperating to navigate through a conflict area. Adversarial attacks such as Sybil attacks can cause safety violations resulting in collisions and traffic jams. In addition, uncooperative (but not necessarily adversarial) CAVs can also induce similar adversarial effects on the traffic network. We propose a decentralized resilient control and coordination scheme that mitigates the effects of adversarial attacks and uncooperative CAVs by utilizing a trust framework. Our trust-aware scheme can guarantee safe collision free coordination and mitigate traffic jams. Simulation results validate the theoretical guarantee of our proposed scheme, and demonstrate that it can effectively mitigate adversarial effects across different traffic scenarios.

arXiv:2305.14654

Barkour: Benchmarking Animal-level Agility with Quadruped Robots

Animals have evolved various agile locomotion strategies, such as sprinting, leaping, and jumping. There is a growing interest in developing legged robots that move like their biological counterparts and show various agile skills to navigate complex environments quickly. Despite the interest, the field lacks systematic benchmarks to measure the performance of control policies and hardware in agility. We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. This encourages researchers to develop controllers that not only move fast, but do so in a controllable and versatile way. To set strong baselines, we present two methods for tackling the benchmark. In the first approach, we train specialist locomotion skills using on-policy reinforcement learning methods and combine them with a high-level navigation controller. In the second approach, we distill the specialist skills into a Transformer-based generalist locomotion policy, named Locomotion-Transformer, that can handle various terrains and adjust the robot's gait based on the perceived environment and robot states. Using a custom-built quadruped robot, we demonstrate that our method can complete the course at half the speed of a dog. We hope that our work represents a step towards creating controllers that enable robots to reach animal-level agility.

arXiv:2305.14260

R2H: Building Multimodal Navigation Helpers that Respond to Help Requests

Intelligent navigation-helper agents are critical as they can navigate users in unknown areas through environmental awareness and conversational ability, serving as potential accessibility tools for individuals with disabilities. In this work, we first introduce a novel benchmark, Respond to Help Requests (R2H), to promote the development of multi-modal navigation helpers capable of responding to requests for help, utilizing existing dialog-based embodied datasets. R2H mainly includes two tasks: (1) Respond to Dialog History (RDH), which assesses the helper agent's ability to generate informative responses based on a given dialog history, and (2) Respond during Interaction (RdI), which evaluates the effectiveness and efficiency of the response during consistent cooperation with a task performer. Furthermore, we explore two approaches to construct the navigation-helper agent, including fine-tuning a novel task-oriented multi-modal response generation model that can see and respond, named SeeRee, and employing a multi-modal large language model in a zero-shot manner. Analysis of the task and method was conducted based on both automatic benchmarking and human evaluations. Project website: https://sites.google.com/view/response2helprequests/home.

arXiv:2305.14268

Masked Path Modeling for Vision-and-Language Navigation

Vision-and-language navigation (VLN) agents are trained to navigate in real-world environments by following natural language instructions. A major challenge in VLN is the limited availability of training data, which hinders the models' ability to generalize effectively. Previous approaches have attempted to address this issue by introducing additional supervision during training, often requiring costly human-annotated data that restricts scalability. In this paper, we introduce a masked path modeling (MPM) objective, which pretrains an agent using self-collected data for downstream navigation tasks. Our proposed method involves allowing the agent to actively explore navigation environments without a specific goal and collect the paths it traverses. Subsequently, we train the agent on this collected data to reconstruct the original path given a randomly masked subpath. This way, the agent can actively accumulate a diverse and substantial amount of data while learning conditional action generation. To evaluate the effectiveness of our technique, we conduct experiments on various VLN datasets and demonstrate the versatility of MPM across different levels of instruction complexity. Our results exhibit significant improvements in success rates, with enhancements of 1.32\%, 1.05\%, and 1.19\% on the val-unseen split of the Room-to-Room, Room-for-Room, and Room-across-Room datasets, respectively. Furthermore, we conduct an analysis that highlights the potential for additional improvements when the agent is allowed to explore unseen environments prior to testing.

arXiv:2305.11953

Quantifying stimulus-relevant representational drift using cross-modality contrastive learning

Previous works investigating representational drift from sensory to central nervous systems converged to show that neural coding, especially at the population level, readily overcomes these session-to-session fluctuations. However, representational drift in the primary visual cortex is more prominent when presenting naturalistic stimuli than artificial stimuli. Animals continuously navigate natural environments during the evolutionary timescale. Why did evolution not get rid of representational drift if it was just an inconvenience? Here, we investigate how representational drift simultaneously influences the encoding of multiple behaviorally relevant features in a natural movie stimulus. Because natural environments contain multiple interacting spatio-temporal features, previous works only provided incomplete understanding of representational drift because of such simplification. Here, we use cross modality contrastive learning to learn an embedding of neural activity that retains only those relevant components of the natural movie stimulus. We also observe that our learned embedding is near-optimal in decoding a whole suite of natural features (scene, optic flow, complex spatio-temporal features, and time) and generalizable to decode those features from single-trial or novel hold-out data. Using this embedding as a surrogate model, we observe that representational drift perturbs the local geometry of the embedding, and this results in various changes in performance when we decode from a different session (90 min later) even at the population level. Our work further suggests that a separate compensation mechanism may be necessary for the optic flow features, as their autocorrelation scale is shorter than the minimum time needed to discriminate scene texture features. Thus, representational drift may encourage neural processing flexibility rather than be a mere nuisance.

arXiv:2305.12935

CrowdWeb: A Visualization Tool for Mobility Patterns in Smart Cities

Human mobility patterns refer to the regularities and trends in the way people move, travel, or navigate through different geographical locations over time. Detecting human mobility patterns is essential for a variety of applications, including smart cities, transportation management, and disaster response. The accuracy of current mobility prediction models is less than 25%. The low accuracy is mainly due to the fluid nature of human movement. Typically, humans do not adhere to rigid patterns in their daily activities, making it difficult to identify hidden regularities in their data. To address this issue, we proposed a web platform to visualize human mobility patterns by abstracting the locations into a set of places to detect more realistic patterns. However, the platform was initially designed to detect individual mobility patterns, making it unsuitable for representing the crowd in a smart city scale. Therefore, we extend the platform to visualize the mobility of multiple users from a city-scale perspective. Our platform allows users to visualize a graph of visited places based on their historical records using a modified PrefixSpan approach. Additionally, the platform synchronizes, aggregates, and displays crowd mobility patterns across various time intervals within a smart city. We showcase our platform using a real dataset.

arXiv:2305.12892공식 코드 · Papers with Code

Bio-inspired spike-based Hippocampus and Posterior Parietal Cortex models for robot navigation and environment pseudo-mapping

The brain has a great capacity for computation and efficient resolution of complex problems, far surpassing modern computers. Neuromorphic engineering seeks to mimic the basic principles of the brain to develop systems capable of achieving such capabilities. In the neuromorphic field, navigation systems are of great interest due to their potential applicability to robotics, although these systems are still a challenge to be solved. This work proposes a spike-based robotic navigation and environment pseudomapping system formed by a bio-inspired hippocampal memory model connected to a Posterior Parietal Cortex model. The hippocampus is in charge of maintaining a representation of an environment state map, and the PPC is in charge of local decision-making. This system was implemented on the SpiNNaker hardware platform using Spiking Neural Networks. A set of real-time experiments was applied to demonstrate the correct functioning of the system in virtual and physical environments on a robotic platform. The system is able to navigate through the environment to reach a goal position starting from an initial position, avoiding obstacles and mapping the environment. To the best of the authors knowledge, this is the first implementation of an environment pseudo-mapping system with dynamic learning based on a bio-inspired hippocampal memory.

arXiv:2305.12411

Synthesizing Diverse Human Motions in 3D Indoor Scenes

We present a novel method for populating 3D indoor scenes with virtual humans that can navigate in the environment and interact with objects in a realistic manner. Existing approaches rely on training sequences that contain captured human motions and the 3D scenes they interact with. However, such interaction data are costly, difficult to capture, and can hardly cover all plausible human-scene interactions in complex environments. To address these challenges, we propose a reinforcement learning-based approach that enables virtual humans to navigate in 3D scenes and interact with objects realistically and autonomously, driven by learned motion control policies. The motion control policies employ latent motion action spaces, which correspond to realistic motion primitives and are learned from large-scale motion capture data using a powerful generative motion model. For navigation in a 3D environment, we propose a scene-aware policy with novel state and reward designs for collision avoidance. Combined with navigation mesh-based path-finding algorithms to generate intermediate waypoints, our approach enables the synthesis of diverse human motions navigating in 3D indoor scenes and avoiding obstacles. To generate fine-grained human-object interactions, we carefully curate interaction goal guidance using a marker-based body representation and leverage features based on the signed distance field (SDF) to encode human-scene proximity relations. Our method can synthesize realistic and diverse human-object interactions (e.g.,~sitting on a chair and then getting up) even for out-of-distribution test scenarios with different object shapes, orientations, starting body positions, and poses. Experimental results demonstrate that our approach outperforms state-of-the-art methods in terms of both motion naturalness and diversity. Code and video results are available at: https://zkf1997.github.io/DIMOS.

arXiv:2305.12088

Game-Theoretical Analysis of Reviewer Rewards in Peer-Review Journal Systems: Analysis and Experimental Evaluation using Deep Reinforcement Learning

In this paper, we navigate the intricate domain of reviewer rewards in open-access academic publishing, leveraging the precision of mathematics and the strategic acumen of game theory. We conceptualize the prevailing voucher-based reviewer reward system as a two-player game, subsequently identifying potential shortcomings that may incline reviewers towards binary decisions. To address this issue, we propose and mathematically formalize an alternative reward system with the objective of mitigating this bias and promoting more comprehensive reviews. We engage in a detailed investigation of the properties and outcomes of both systems, employing rigorous game-theoretical analysis and deep reinforcement learning simulations. Our results underscore a noteworthy divergence between the two systems, with our proposed system demonstrating a more balanced decision distribution and enhanced stability. This research not only augments the mathematical understanding of reviewer reward systems, but it also provides valuable insights for the formulation of policies within journal review system. Our contribution to the mathematical community lies in providing a game-theoretical perspective to a real-world problem and in the application of deep reinforcement learning to simulate and understand this complex system.

arXiv:2305.11204

Assessing Exoplanet Habitability through Data-driven Approaches: A Comprehensive Literature Review

The exploration and study of exoplanets remain at the frontier of astronomical research, challenging scientists to continuously innovate and refine methodologies to navigate the vast, complex data these celestial bodies produce. This literature the review aims to illuminate the emerging trends and advancements within this sphere, specifically focusing on the interplay between exoplanet detection, classification, and visualization, and the the increasingly pivotal role of machine learning and computational models. Our journey through this realm of exploration commences with a comprehensive analysis of fifteen meticulously selected, seminal papers in the field. These papers, each representing a distinct facet of exoplanet research, collectively offer a multi-dimensional perspective on the current state of the field. They provide valuable insights into the innovative application of machine learning techniques to overcome the challenges posed by the analysis and interpretation of astronomical data. From the application of Support Vector Machines (SVM) to Deep Learning models, the review encapsulates the broad spectrum of machine learning approaches employed in exoplanet research. The review also seeks to unravel the story woven by the data within these papers, detailing the triumphs and tribulations of the field. It highlights the increasing reliance on diverse datasets, such as Kepler and TESS, and the push for improved accuracy in exoplanet detection and classification models. The narrative concludes with key takeaways and insights, drawing together the threads of research to present a cohesive picture of the direction in which the field is moving. This literature review, therefore, serves not just as an academic exploration, but also as a narrative of scientific discovery and innovation in the quest to understand our cosmic neighborhood.

arXiv:2305.10408

Extracting Blockchain Concepts from Text

Blockchains provide a mechanism through which mutually distrustful remote parties can reach consensus on the state of a ledger of information. With the great acceleration with which this space is developed, the demand for those seeking to learn about blockchain also grows. Being a technical subject, it can be quite intimidating to start learning. For this reason, the main objective of this project was to apply machine learning models to extract information from whitepapers and academic articles focused on the blockchain area to organize this information and aid users to navigate the space.

arXiv:2305.09788공식 코드 · Papers with Code

Codesign of Edge Intelligence and Automated Guided Vehicle Control

This work presents a harmonic design of autonomous guided vehicle (AGV) control, edge intelligence, and human input to enable autonomous transportation in industrial environments. The AGV has the capability to navigate between a source and destinations and pick/place objects. The human input implicitly provides preferences of the destination and exact drop point, which are derived from an artificial intelligence (AI) module at the network edge and shared with the AGV over a wireless network. The demonstration indicates that the proposed integrated design of hardware, software, and AI design achieve a technology readiness level (TRL) of range 4-5

arXiv:2305.09330

Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluation

In the current landscape of ever-increasing levels of digitalization, we are facing major challenges pertaining to scalability. Recommender systems have become irreplaceable both for helping users navigate the increasing amounts of data and, conversely, aiding providers in marketing products to interested users. The growing awareness of discrimination in machine learning methods has recently motivated both academia and industry to research how fairness can be ensured in recommender systems. For recommender systems, such issues are well exemplified by occupation recommendation, where biases in historical data may lead to recommender systems relating one gender to lower wages or to the propagation of stereotypes. In particular, consumer-side fairness, which focuses on mitigating discrimination experienced by users of recommender systems, has seen a vast number of diverse approaches for addressing different types of discrimination. The nature of said discrimination depends on the setting and the applied fairness interpretation, of which there are many variations. This survey serves as a systematic overview and discussion of the current research on consumer-side fairness in recommender systems. To that end, a novel taxonomy based on high-level fairness interpretation is proposed and used to categorize the research and their proposed fairness evaluation metrics. Finally, we highlight some suggestions for the future direction of the field.

arXiv:2305.08510

Fast Traversability Estimation for Wild Visual Navigation

Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes. In this work, we propose Wild Visual Navigation (WVN), an online self-supervised learning system for traversability estimation which uses only vision. The system is able to continuously adapt from a short human demonstration in the field. It leverages high-dimensional features from self-supervised visual transformer models, with an online scheme for supervision generation that runs in real-time on the robot. We demonstrate the advantages of our approach with experiments and ablation studies in challenging environments in forests, parks, and grasslands. Our system is able to bootstrap the traversable terrain segmentation in less than 5 min of in-field training time, enabling the robot to navigate in complex outdoor terrains - negotiating obstacles in high grass as well as a 1.4 km footpath following. While our experiments were executed with a quadruped robot, ANYmal, the approach presented can generalize to any ground robot.

arXiv:2305.08698공식 코드 · Papers with Code

Continual Multimodal Knowledge Graph Construction

Current Multimodal Knowledge Graph Construction (MKGC) models struggle with the real-world dynamism of continuously emerging entities and relations, often succumbing to catastrophic forgetting-loss of previously acquired knowledge. This study introduces benchmarks aimed at fostering the development of the continual MKGC domain. We further introduce MSPT framework, designed to surmount the shortcomings of existing MKGC approaches during multimedia data processing. MSPT harmonizes the retention of learned knowledge (stability) and the integration of new data (plasticity), outperforming current continual learning and multimodal methods. Our results confirm MSPT's superior performance in evolving knowledge environments, showcasing its capacity to navigate balance between stability and plasticity.

arXiv:2305.07421

Selective imitation on the basis of reward function similarity

Imitation is a key component of human social behavior, and is widely used by both children and adults as a way to navigate uncertain or unfamiliar situations. But in an environment populated by multiple heterogeneous agents pursuing different goals or objectives, indiscriminate imitation is unlikely to be an effective strategy -- the imitator must instead determine who is most useful to copy. There are likely many factors that play into these judgements, depending on context and availability of information. Here we investigate the hypothesis that these decisions involve inferences about other agents' reward functions. We suggest that people preferentially imitate the behavior of others they deem to have similar reward functions to their own. We further argue that these inferences can be made on the basis of very sparse or indirect data, by leveraging an inductive bias toward positing the existence of different \textit{groups} or \textit{types} of people with similar reward functions, allowing learners to select imitation targets without direct evidence of alignment.

arXiv:2305.06566공식 코드 · Papers with Code

ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models

Personalized content-based recommender systems have become indispensable tools for users to navigate through the vast amount of content available on platforms like daily news websites and book recommendation services. However, existing recommenders face significant challenges in understanding the content of items. Large language models (LLMs), which possess deep semantic comprehension and extensive knowledge from pretraining, have proven to be effective in various natural language processing tasks. In this study, we explore the potential of leveraging both open- and closed-source LLMs to enhance content-based recommendation. With open-source LLMs, we utilize their deep layers as content encoders, enriching the representation of content at the embedding level. For closed-source LLMs, we employ prompting techniques to enrich the training data at the token level. Through comprehensive experiments, we demonstrate the high effectiveness of both types of LLMs and show the synergistic relationship between them. Notably, we observed a significant relative improvement of up to 19.32% compared to existing state-of-the-art recommendation models. These findings highlight the immense potential of both open- and closed-source of LLMs in enhancing content-based recommendation systems. We will make our code and LLM-generated data available for other researchers to reproduce our results.