检索结果-内蒙古大学图书馆

Optimizing NeRF-based SLAM with Trajectory Smoothness Constraints

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Yicheng Chen, Guangcheng Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

The joint optimization of Neural Radiance Fields (NeRF) and camera trajectories has been widely applied in SLAM tasks due to its superior dense mapping quality and consistency. NeRF-based SLAM learns camera poses using constraints by implicit map representation. A widely observed phenomenon that results from the constraints of this form is jerky and physically unrealistic estimated camera motion, which in turn affects the map quality. To address this deficiency of current NeRF-based SLAM, we propose in this paper TS-SLAM (TS for Trajectory Smoothness). It introduces smoothness constraints on camera trajectories by representing them with uniform cubic B-splines with continuous acceleration that guarantees smooth camera motion. Benefiting from the differentiability and local control properties of B-splines, TS-SLAM can incrementally learn the control points end-to-end using a sliding window paradigm. Additionally, we regularize camera trajectories by exploiting the dynamics prior to further smooth trajectories. Experimental results demonstrate that TS-SLAM achieves superior trajectory accuracy and improves mapping quality versus NeRF-based SLAM that does not employ the above smoothness constraints. © 2024, CC BY.

关键词： Mapping

RTAGrasp: Learning Task-Oriented Grasping from Human Videos via Retrieval, Transfer, and Alignment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dong, Wenlong Huang, Dehao Liu, Jiangshan Tang, Chao Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

Task-oriented grasping (TOG) is crucial for robots to accomplish manipulation tasks, requiring the determination of TOG positions and directions. Existing methods either rely on costly manual TOG annotations or only extract coarse grasping positions or regions from human demonstrations, limiting their practicality in real-world applications. To address these limitations, we introduce RTAGrasp, a Retrieval, Transfer, and Alignment framework inspired by human grasping strategies. Specifically, our approach first effortlessly constructs a robot memory from human grasping demonstration videos, extracting both TOG position and direction constraints. Then, given a task instruction and a visual observation of the target object, RTAGrasp retrieves the most similar human grasping experience from its memory and leverages semantic matching capabilities of vision foundation models to transfer the TOG constraints to the target object in a training-free manner. Finally, RTAGrasp aligns the transferred TOG constraints with the robot’s action for execution. Evaluations on the public TOG benchmark, TaskGrasp dataset, show the competitive performance of RTAGrasp on both seen and unseen object categories compared to existing baseline methods. Real-world experiments further validate its effectiveness on a robotic arm. Our code, appendix, and video are available at https: //***/view/rtagrasp/home. © 2024, CC BY.

关键词： Robotic arms

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

Comparative Study of Mooney Viscosity Prediction Models for Rubber Compounds based on ANFIS with Different Architectures 6

学校读者我要写书评

暂无评论

Comparative Study of Mooney Viscosity Prediction Models for ...

6th International Conference on Business and Industrial Research, ICBIR 2021

作者： Sapsiriroht, Palida Kittipeerachon, Kanticha Thai Nichi Institute of Technology Faculty of Engineering Bangkok Thailand Thai Nichi Institute of Technology Computer Engineering Robotics and Technology Laboratory Bangkok Thailand

ISBN: (纸本)9781665433495

Mooney viscosity is an important parameter in rubber compound industry because it is one of the processing windows and key properties of a rubber compound. As dynamic behaviors of rubber compounds are nonlinear and rubber product manufacturing process affects dynamic behaviors, an exact model for predicting Mooney viscosity has not been found. This paper presents the prediction models based on Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for rubber compounds with different architectures and the effects of changes of certain parameters in each model on prediction performance. The database is collected from the historical data of manufacturing and then cleansed by removing errors in process and out-of-spec values. Both premise and consequent parameters of rules are created using the parameter initialization algorithm. The effects of different numbers of inputs and epochs, different input variables, and different interpretation methods are investigated. The simulation results show that the minimum value of RMSE for data testing is obtained by using the parameters initialization algorithm with 100 epochs, 3 inputs and OR interpretation method. Moreover, the lower number of epochs indicates the faster processing of the model. It is expected that the Mooney viscosity can be predicted and shown immediately at the end of mixing process. © 2021 IEEE.

关键词： Parameter estimation

Model Predictive Path Integral Control of I2RIS Robot Using RBF Identifier and Extended Kalman Filter

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Esfandiari, Mojtaba Du, Pengyuan Wei, Haochen Gehlbach, Peter Munawar, Adnan Kazanzides, Peter Iordachita, Iulian Department of Mechanical Engineering Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Department of Computer Science Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Wilmer Eye Institute Johns Hopkins Hospital BaltimoreMD21287 United States

Modeling and controlling cable-driven snake robots is a challenging problem due to nonlinear mechanical properties such as hysteresis, variable stiffness, and unknown friction between the actuation cables and the robot body. This challenge is more significant for snake robots in ophthalmic surgery applications, such as the Improved Integrated Robotic Intraocular Snake (I2RIS), given its small size and lack of embedded sensory feedback. Data-driven models take advantage of global function approximations, reducing complicated analytical models’ challenge and computational costs. However, their performance might deteriorate in case of new data unseen in the training phase. Therefore, adding an adaptation mechanism might improve these models’ performance during snake robots’ interactions with unknown environments. In this work, we applied a model predictive path integral (MPPI) controller on a data-driven model of the I2RIS based on the Gaussian mixture model (GMM) and Gaussian mixture regression (GMR). To analyze the performance of the MPPI in unseen robot-tissue interaction situations, unknown external disturbances and environmental loads are simulated and added to the GMM-GMR model. These uncertainties of the robot model are then identified online using a radial basis function (RBF) whose weights are updated using an extended Kalman filter (EKF). Simulation results demonstrated the robustness of the optimal control solutions of the MPPI algorithm and its computational superiority over a conventional model predictive control (MPC) algorithm. © 2025, CC BY.

关键词： Extended Kalman filters

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

Adaptive Block Elevation Mapping for Large-scale Scene

学校读者我要写书评

暂无评论

Adaptive Block Elevation Mapping for Large-scale Scene

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Zhou, Yang Zhu, Shiqiang Huang, Huang Li, Yuehua Gu, Jason The Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China The Beijing Institute of Control Engineering Beijing100094 China The Beijing Research Institute Zhejiang Laboratory Beijing100094 China The Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9781665481090

Dense map that contains the surrounding geometry and vision information of a robot is widely used for path planning, navigation, obstacle avoidance and other applications. Considering the performance of the processing unit mounted on the robot is limited, mapping algorithm has to make compromise by sacrificing speed and precision. It will be more challenging when the dense mapping scene is very large because the memory consumption will be greatly increased and the map is difficult to be extended if beyonding the initial map. To suppress the negative impact from the increased map scale, we proposed a novel block mapping approach to generate the dense map in large scale of scene. In this work, the elevation map is selected as the base dense map. The entire elevation map is segmented into numerous block maps of which size is much smaller than that of the entire map. The present moment of lidar and vision measurements are used to generate the local elevation map. The local elevation map is used to update block maps which are adaptively generated along the motion trajectory. A memory-disk interaction mechanism, which the block maps will be loaded to memory or saved to local disk when needed, is introduced. Our block mapping approach is tested on the KITTI datasets, and the results demonstrate that the mapping approach can stably operate in a large scale of scene with a much smaller consumption of memory. © 2022 IEEE.

关键词： Motion planning

LucidGrasp: Robotic Framework for Autonomous Manipulation of laboratory Equipment with Different Degrees of Transparency via 6D Pose Estimation

学校读者我要写书评

暂无评论

LucidGrasp: Robotic Framework for Autonomous Manipulation of...

IEEE International Conference on robotics and Biomimetics

作者： Maria Makarova Daria Trinitatova Qian Liu Dzmitry Tsetserukou Intelligent Space Robotics Laboratory Center for Digital Engineering Skolkovo Institute of Science and Technology (Skoltech) Moscow Russia Department of Computer Science and Technology Dalian University of Technology China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Many modern robotic systems operate autonomously, however they often lack the ability to accurately analyze the environment and adapt to changing external conditions, while teleoperation systems often require special operator skills. In the field of laboratory automation, the number of automated processes is growing, however such systems are usually developed to perform specific tasks. In addition, many of the objects used in this field are transparent, making it difficult to analyze them using visual channels. The contributions of this work include the development of a robotic framework with autonomous mode for manipulating liquid-filled objects with different degrees of transparency in complex pose combinations. The conducted experiments demonstrated the robustness of the designed visual perception system to accurately estimate object poses for autonomous manipulation, and confirmed the performance of the algorithms in dexterous operations such as liquid dispensing. The proposed robotic framework can be applied for laboratory automation, since it allows solving the problem of performing non-trivial manipulation tasks with the analysis of object poses of varying degrees of transparency and liquid levels, requiring high accuracy and repeatability.

关键词： Visualization Liquids Automation Accuracy Biomimetics Pose estimation Robustness Robots Visual perception

Visual Sensor-Based Trajectory Multimodality Prediction via Anchor-Free Query Attention Network

学校读者我要写书评

暂无评论

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Wang, Ruiping Cheng, Jun Yu, Junzhi Nanyang Technological University School of Computer Science and Engineering Jurong West Singapore639798 Singapore Peking University College of Engineering Beijing100871 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China

As a core component of intelligent surveillance and autonomous driving systems, visual sensor-based trajectory multimodality prediction can significantly improve their perception and decision-making capabilities. Numerous existing trajectory prediction methods are dedicated to enhance prediction performance. However, they still fail to effectively model the complex spatiotemporal interactions among pedestrians and trajectory multimodality. To address the above challenges, this article presents one new trajectory multimodality prediction method via anchor-free query-based attention network, which can more effectively capture spatiotemporal interactions and model trajectory multimodality. First, the initial trajectory proposal module employs target-centered query-based attention to capture complex spatiotemporal interactions and generate multiple trajectory proposals corresponding to the multiple modes of the future trajectory, which allows the model to use different interaction information when decoding trajectory points at different time steps. Second, the novel trajectory refinement module utilizes the learnable trajectory proposals to construct proposal-level interaction mechanisms to refine future trajectories. Experimental results conducted on ETH and UCY datasets demonstrate that the proposed model can provide the state-of-the-art prediction performance. © 1963-2012 IEEE.

关键词： Prediction models