检索结果-内蒙古大学图书馆

Bridging the Communication Gap: Artificial Agents Learning Sign Language Through Imitation 16th

学校读者我要写书评

暂无评论

Bridging the Communication Gap: Artificial Agents Learning ...

16th International Conference on Social robotics, ICSR + AI 2024

作者： Tavella, Federico Galata, Aphrodite Cangelosi, Angelo Manchester Centre for Robotics and AI University of Manchester ManchesterM13 9PL United Kingdom Department of Computer Science University of Manchester ManchesterM13 9PL United Kingdom

ISBN: (纸本)9789819635214

This paper explores acquiring non-verbal communication skills through learning from demonstrations, with potential applications in sign language comprehension and expression. In particular, we focus on imitation learning for artificial agents, exemplified by teaching a simulated humanoid American Sign Language. We use computer vision and deep learning to extract information from videos, and reinforcement learning to enable the agent to replicate observed actions. Compared to other methods, our approach eliminates the need for additional hardware to acquire information. We demonstrate how the combination of these different techniques offers a viable way to learn sign language. Our methodology successfully teaches 5 different signs involving the upper body (i.e., arms and hands). This research paves the way for advanced communication skills in artificial agents. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Chatbots

Gravity Compensation of the dVRK-Si Patient Side Manipulator based on Dynamic Model Identification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhou, Haoying Yang, Hao Deguet, Anton Fichera, Loris Wu, Jie Ying Kazanzides, Peter Department of Robotics Engineering Worcester Polytechnic Institute MA United States Laboratory for Computational Sensing and Robotics JHU MD United States Department of Computer Science Vanderbilt University TN United States Department of Computer Science Johns Hopkins University MD United States

The da Vinci Research Kit (dVRK, also known as dVRK Classic) is anopen-source teleoperated surgical robotic system whose hardware is obtainedfrom the first generation da Vinci Surgical System (Intuitive, Sunnyvale, CA,USA). The dVRK has greatly facilitated research in robot-assisted surgery overthe past decade and helped researchers address multiple major challenges inthis domain. Recently, the dVRK-Si system, a new version of the dVRK which usesmechanical components from the da Vinci Si Surgical System, became available tothe community. The major difference between the first generation da Vinci andthe da Vinci Si is in the structural upgrade of the Patient Side Manipulator(PSM). Because of this upgrade, the gravity of the dVRK-Si PSM can no longer beignored as in the dVRK Classic. The high gravity offset may lead to relativelylow control accuracy and longer response time. In addition, althoughsubstantial progress has been made in addressing the dynamic modelidentification problem for the dVRK Classic, further research is required onmodel-based control for the dVRK-Si, due to differences in mechanicalcomponents and the demand for enhanced control performance. To address theseproblems, in this work, we present (1) a novel full kinematic model of thedVRK-Si PSM, and (2) a gravity compensation approach based on the dynamic modelidentification. © 2025, CC BY.

关键词： Surgical equipment

EFFICIENT IMITATION UNDER MISSPECIFICATION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Espinosa-Dice, Nicolas Choudhury, Sanjiban Sun, Wen Swamy, Gokul Department of Computer Science Cornell University United States Robotics Institute Carnegie Mellon University United States

We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true in practice due to differences in observation space and action space expressiveness (e.g. perceptual or morphological differences between robots and humans). Given the learner must make some mistakes in the misspecified setting, interaction with the environment is fundamentally required to figure out which mistakes are particularly costly and lead to compounding errors. However, given the computational cost and safety concerns inherent in interaction, we would like to perform as little of it as possible while ensuring we have learned a strong policy. Accordingly, prior work has proposed a flavor of efficient inverse reinforcement learning algorithms that merely perform a computationally efficient local search procedure with strong guarantees in the realizable setting. We first prove that under a novel structural condition we term reward-agnostic policy completeness, these sorts of local-search based IRL algorithms are able to avoid compounding errors. We then consider the question of where we should perform local search in the first place, given the learner may not be able to "walk on a tightrope" as well as the expert in the misspecified setting. We prove that in the misspecified setting, it is beneficial to broaden the set of states on which local search is performed to include states reachable by good policies that the learner can actually play. We then experimentally explore a variety of sources of misspecification and how offline data can be used to effectively broaden where we perform local search from. © 2025, CC BY.

关键词： Learning algorithms

ENHANCING SMART ENVIRONMENTS WITH CONTEXT-AWARE CHATBOTS USING LARGE LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Polo-Rodríguez, Aurora Fiorini, Laura Rovini, Erika Cavallo, Filippo Medina-Quero, Javier Department of Computer Science Automatics and Robotics University of Granada Granada Spain Department of Industrial Engineering University of Florence Florence Italy

This work presents a novel architecture for context-aware interactions within smart environments, leveraging Large Language Models (LLMs) to enhance user experiences. Our system integrates user location data obtained through UWB tags and sensor-equipped smart homes with real-time human activity recognition (HAR) to provide a comprehensive understanding of user context. This contextual information is then fed to an LLM-powered chatbot, enabling it to generate personalised interactions and recommendations based on the user’s current activity and environment. This approach moves beyond traditional static chatbot interactions by dynamically adapting to the user’s real-time situation. A case study conducted from a real-world dataset demonstrates the feasibility and effectiveness of our proposed architecture, showcasing its potential to create more intuitive and helpful interactions within smart homes. The results highlight the significant benefits of integrating LLM with real-time activity and location data to deliver personalised and contextually relevant user experiences. © 2025, CC BY-NC-SA.

关键词： Smart homes

Clustering-Based Artificial Rabbit Optimization: Approach for Enhanced Data Clustering

学校读者我要写书评

暂无评论

Clustering-Based Artificial Rabbit Optimization: Approach fo...

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Balqees Ayal-Awwad Jamil Al-Sawwa Mohammad Almseidin Maen Alzubi Computer Science Department Tafila Technical University Tafila Jordan Department of Robotics and Artificial Intelligence Jadara University Irbid Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Data clustering is a data mining task used to group data points based on their similarity. The goal of clustering is to divide $N$ data points into $K$ clusters while minimizing the intra-cluster distance and maximizing the inter-cluster distance. Data clustering can be viewed as a combinatorial optimization problem, which is known as NP-hard. Thus, nature-inspired optimization algorithms have been applied to find better solutions for clustering problems. In this paper, the clustering-based artificial rabbit optimization (CARO) method is proposed. The main idea is to find the optimal centroids for the $K$ clusters by minimizing the sum of squared errors. Using seven benchmark datasets, the experimental results showed that the CARO achieved outstanding results compared to six nature-inspired optimization algorithms in terms of purity and entropy.

关键词： Rabbits Clustering algorithms Machine learning Benchmark testing Feature extraction Entropy Reliability Data mining Optimization Convergence

Towards Collaborative Simultaneous Localization and Mapping: A Survey of the Current Research Landscape

学校读者我要写书评

暂无评论

Field Robotics

Field robotics 2025年 2卷 971-1000页

作者： Pierre-Yves Lajoie Benjamin Ramtoula Fang Wu Giovanni Beltrame Department of Computer and Software Engineering Polytechnique Montréal Canada Oxford Robotics Institute Department of Engineering Science University of Oxford United Kingdom Desay SV Automotive Singapore

Motivated by the tremendous progress, we witnessed in recent years, this paper presents a survey of the scientific literature on the topic of Collaborative Simultaneous Localization and Mapping (C-SLAM), also known as multi-robot SLAM. With fleets of self-driving cars on the horizon and the rise of multi-robot systems in industrial applications, we believe that Collaborative SLAM will soon become a cornerstone of future robotic applications. In this survey, we introduce the basic concepts of C-SLAM and present a thorough literature review. We also outline the major challenges and limitations of C-SLAM in terms of robustness, communication, and resource management. We conclude by exploring the area's current trends and promising research avenues.

关键词： Robots Simultaneous localization and mapping Robot kinematics Robot sensing systems Collaboration Surveys Multi-robot systems Sensors Market research Trajectory

BIRD: Battlefield-Integrated Reconnaissance Drone with VQA

学校读者我要写书评

暂无评论

BIRD: Battlefield-Integrated Reconnaissance Drone with VQA

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Rayon, Nathan Menser, Kobi Catalano, Louis Vega, Jonathan Najarro, Julio Sevil, Hakki Erhan Department of Computer Science University of West Florida FL32514 United States Department of Mechanical Engineering University of West Florida FL32514 United States Catalano Aerospace LLC FL32502 United States Department of Intelligent Systems & Robotics University of West Florida FL32514 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This paper introduces a new unmanned aerial system (UAS) design featuring coaxial rotors and tethered operation with a base station. The coaxial rotor configuration enhances stability and maneuverability, particularly in challenging environments. The tethered connection to a base station ensures prolonged flight duration and enables continuous power and data transmission. Moreover, the UAS incorporates a visual question answering (VQA) based target identification system. This system leverages advanced computer vision algorithms to analyze visual input from onboard cameras, coupled with natural language processing techniques to interpret and respond to queries regarding identified targets. The integration of VQA technology enables critical decision-making decisions through providing crucial information identify about targets in real-time scenarios. The new design has a significant potential for applications in surveillance, reconnaissance, search and rescue, and disaster response, as this design was conceptualized to provide persistent Intelligence, Reconnaissance & Surveillance (ISR) capabilities. Further analysis of the concept design was conducted to investigate the feasibility of novel design characteristics. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Reconnaissance aircraft

Toward a Low-Cost Perception System in Autonomous Vehicles: A Spectrum Learning Approach

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Alsakabi, Mohammed Erickson, Aidan Dolan, John M. Tonguz, Ozan K. Department of Electrical and Computer Engineering College of Engineering The Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States

We present a cost-effective new approach for generating denser depth maps for Autonomous Driving (AD) and Autonomous Vehicles (AVs) by integrating the images obtained from deep neural network (DNN) 4D radar detectors with conventional camera RGB images. Our approach introduces a novel pixel positional encoding algorithm inspired by Bartlett’s spatial spectrum estimation technique. This algorithm transforms both radar depth maps and RGB images into a unified pixel image subspace called the Spatial Spectrum, facilitating effective learning based on their similarities and differences. Our method effectively leverages high-resolution camera images to train radar depth map generative models, addressing the limitations of conventional radar detectors in complex vehicular environments, thus sharpening the radar output. We develop spectrum estimation algorithms tailored for radar depth maps and RGB images, a comprehensive training framework for data-driven generative models, and a camera-radar deployment scheme for AV operation. Our results demonstrate that our approach also outperforms the state-of-the-art (SOTA) by 27.95% in terms of Unidirectional Chamfer Distance (UCD). © 2025, CC BY-NC-ND.

关键词： Radar imaging

NOISE-CONDITIONED ENERGY-BASED ANNEALED REWARDS (NEAR): A GENERATIVE FRAMEWORK FOR IMITATION LEARNING FROM OBSERVATION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Diwan, Anish Abhijit Urain, Julen Kober, Jens Peters, Jan Department of Cognitive Robotics TU Delft Netherlands Department of Computer Science TU Darmstadt Germany Germany Center for Cognitive Science TU Darmstadt Germany Germany

This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert’s motion data distribution and learns smooth, and well-defined representations of the data distribution’s energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via reinforcement learning. We also present a strategy to gradually switch between the learnt energy functions, ensuring that the learnt rewards are always well-defined in the manifold of policy-generated samples. We evaluate our algorithm on complex humanoid tasks such as locomotion and martial arts and compare it with state-only adversarial imitation learning algorithms like Adversarial Motion Priors (AMP). Our framework sidesteps the optimisation challenges of adversarial imitation learning techniques and produces results comparable to AMP in several quantitative metrics across multiple imitation settings. Code and videos available at ***/noise-conditionedenergy-based-annealed-rewards/ © 2025, CC BY.

关键词： Adversarial machine learning