检索结果-内蒙古大学图书馆

Particle Swarm Optimization Tuned Compensation Function Observer Based Control Method for Ship Motion 13

学校读者我要写书评

暂无评论

Particle Swarm Optimization Tuned Compensation Function Obse...

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Ren, Jia Wang, Zhaoxia Chen, Zengqiang Sun, Mingwei Sun, Qinglin College of Artificial Intelligence Nankai University Tianjin300350 China School of Computing and Information Systems Singapore Management University Singapore178902 Singapore Key Lab of Intelligent Robotics of Tianjin Tianjin300350 China

ISBN: (纸本)9798350361674

To achieve more stable and rapid control of ship motion, we proposed the Compensation Function Observer (CFO)-based control algorithm and used the Particle Swarm Optimization (PSO) to adjust its parameters. The performance of the proposed method is compared with PSO based Active Disturbance Rejection Control (ADRC) and traditional ADRC. The simulation results show that the ship motion system controlled by our proposed method has smaller deviation and jitter. Even under different interference, it still has better performance. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Rotondi, Dennis Scaparro, Fabio Blum, Hermann Arras, Kai O. Socially Intelligent Robotics Lab Institute for Artificial Intelligence University of Stuttgart Germany Robot Perception and Learning Lab LAMARR Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

The concept of 3D scene graphs is increasingly recognized as a powerful semantic and hierarchical representation of the environment. Current approaches often address this at a coarse, object-level resolution. In contrast, our goal is to develop a representation that enables robots to directly interact with their environment by identifying both the location of functional interactive elements and how these can be used. To achieve this, we focus on detecting and storing objects at a finer resolution, focusing on affordance-relevant parts. The primary challenge lies in the scarcity of data that extends beyond instance-level detection and the inherent difficulty of capturing detailed object features using robotic sensors. We leverage currently available 3D resources to generate 2D data and train a detector, which is then used to augment the standard 3D scene graph generation pipeline. Through our experiments, we demonstrate that our approach achieves functional element segmentation comparable to state-of-the-art 3D models and that our augmentation enables task-driven affordance grounding with higher accuracy than the current solutions. © 2025, CC BY-NC-ND.

关键词： Semantics

Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kim, Yunho Oh, Hyunsik Lee, Jeonghyun Choi, Jinhyeok Ji, Gwanghyeon Jung, Moonkyu Youm, Donghoon Hwangbo, Jemin Robotics and Artificial Intelligence Lab KAIST Daejeon Korea Republic of

Several earlier studies have shown impressive control performance in complex robotic systems by designing the controller using a neural network and training it with model-free reinforcement learning. However, these outstanding controllers with natural motion style and high task performance are developed through extensive reward engineering, which is a highly laborious and time-consuming process of designing numerous reward terms and determining suitable reward coefficients. In this work, we propose a novel reinforcement learning framework for training neural network controllers for complex robotic systems consisting of both rewards and constraints. To let the engineers appropriately reflect their intent to constraints and handle them with minimal computation overhead, two constraint types and an efficient policy optimization algorithm are suggested. The learning framework is applied to train locomotion controllers for several legged robots with different morphology and physical attributes to traverse challenging terrains. Extensive simulation and real-world experiments demonstrate that performant controllers can be trained with significantly less reward engineering, by tuning only a single reward coefficient. Furthermore, a more straightforward and intuitive engineering process can be utilized, thanks to the interpretability and generalizability of constraints. The summary video is available at https://***/KAlm3yskhvM. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

SAMPLE EFFICIENT DEEP REINFORCEMENT LEARNING VIA UNCERTAINTY ESTIMATION 10

学校读者我要写书评

暂无评论

SAMPLE EFFICIENT DEEP REINFORCEMENT LEARNING VIA UNCERTAINTY...

10th International Conference on Learning Representations, ICLR 2022

作者： Mai, Vincent Mani, Kaustubh Paull, Liam Robotics and Embodied AI Lab Mila - Quebec Institute of Artificial Intelligence Université de Montréal QC Canada

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As this noise is heteroscedastic, its effects can be mitigated using uncertainty-based weights in the optimization process. Previous methods rely on sampled ensembles, which do not capture all aspects of uncertainty. We provide a systematic analysis of the sources of uncertainty in the noisy supervision that occurs in RL, and introduce inverse-variance RL, a Bayesian framework which combines probabilistic ensembles and Batch Inverse Variance weighting. We propose a method whereby two complementary uncertainty estimation methods account for both the Q-value and the environment stochasticity to better mitigate the negative impacts of noisy supervision. Our results show significant improvement in terms of sample efficiency on discrete and continuous control tasks. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Reinforcement learning

Interactive Expressive Motion Generation Using Dynamic Movement Primitives

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hielscher, Till Bulling, Andreas Arras, Kai O. Socially Intelligent Robotics Lab Institute for Artificial Intelligence University of Stuttgart Germany Collaborative Artificial Intelligence Group Institute for Visualization and Interactive Systems University of Stuttgart Germany

Our goal is to enable social robots to interact autonomously with humans in a realistic, engaging, and expressive manner. The 12 Principles of Animation [1] are a well-established framework animators use to create movements that make characters appear convincing, dynamic, and emotionally expressive. This paper proposes a novel approach that leverages Dynamic Movement Primitives (DMPs) to implement key animation principles, providing a learnable, explainable, modulable, online adaptable and composable model for automatic expressive motion generation. DMPs, originally developed for general imitation learning in robotics and grounded in a spring-damper system design, offer mathematical properties that make them particularly suitable for this task. Specifically, they enable modulation of the intensities of individual principles and facilitate the decomposition of complex, expressive motion sequences into learnable and parametrizable primitives. We present the mathematical formulation of the parameterized animation principles and demonstrate the effectiveness of our framework through experiments and application on three robotic platforms with different kinematic configurations, in simulation, on actual robots and in a user study. Our results show that the approach allows for creating diverse and nuanced expressions using a single base model. © 2025, CC BY-NC-ND.

关键词： Animation

Learning Semantic Traversability with Egocentric Video and Automated Annotation Strategy

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kim, Yunho Lee, Jeong Hyun Lee, Choongin Mun, Juhyeok Youm, Donghoon Park, Jeongsoo Hwangbo, Jemin Robotics and Artificial Intelligence Lab KAIST Daejeon Korea Republic of Neuromeka Seoul Korea Republic of

For reliable autonomous robot navigation in urban settings, the robot must have the ability to identify semantically traversable terrains in the image based on the semantic understanding of the scene. This reasoning ability is based on semantic traversability, which is frequently achieved using semantic segmentation models fine-tuned on the testing domain. This fine-tuning process often involves manual data collection with the target robot and annotation by human labelers which is prohibitively expensive and unscalable. In this work, we present an effective methodology for training a semantic traversability estimator using egocentric videos and an automated annotation process. Egocentric videos are collected from a camera mounted on a pedestrian's chest. The dataset for training the semantic traversability estimator is then automatically generated by extracting semantically traversable regions in each video frame using a recent foundation model in image segmentation and its prompting technique. Extensive experiments with videos taken across several countries and cities, covering diverse urban scenarios, demonstrate the high scalability and generalizability of the proposed annotation method. Furthermore, performance analysis and real-world deployment for autonomous robot navigation showcase that the trained semantic traversability estimator is highly accurate, able to handle diverse camera viewpoints, computationally light, and real-world applicable. The summary video is available at https://***/EUVoH-wA-lA. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Human-like Social Learning for Social Robots: A Systematic Review

学校读者我要写书评

暂无评论

Human-like Social Learning for Social Robots: A Systematic R...

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Diana Burkart Barbara Bruno Socially Assistive Robotics With Artificial Intelligence (SARAI) Lab Karlsruhe Institute of Technology (KIT) Germany

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Social learning is a learning paradigm aiming to make the process of teaching new skills to an artificial intelligent agent (such as a robot) as close as possible to the process we employ when teaching skills to other humans. Equipping robot companions with the ability to learn from social interactions with their users would enable naive users to effortlessly teach skills to robots and support personalization and long-term use. Aiming to support research on the field, in this article we present a systematic literature review of human-like social learning for social robots, with a specific focus on works employing real robots and real human-robot social interactions. The review examines relevant papers from perspectives including the type of robot used, the task to be learned, and the method and assessment metrics employed, and allows for the identification of open research avenues.

关键词： Measurement Education Social robots Transfer learning Hidden Markov models Learning (artificial intelligence) Reinforcement learning Planning Robots Lenses

Practical Considerations for Discrete-Time Implementations of Continuous-Time Control Barrier Function-Based Safety Filters

学校读者我要写书评

暂无评论

Practical Considerations for Discrete-Time Implementations o...

American Control Conference (ACC)

作者： Lukas Brunke Siqi Zhou Mingxuan Che Angela P. Schoellig Learning Systems and Robotics Lab Technical University of Munich Germany University of Toronto Canada Munich Institute of Robotics and Machine Intelligence (MIRMI) the University of Toronto Robotics Institute and the Vector Institute for Artificial Intelligence

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

Safety filters based on control barrier functions (CBFs) have become a popular method to guarantee safety for uncertified control policies, e.g., as resulting from reinforcement learning. Here, safety is defined as staying in a pre-defined set, the safe set, that adheres to the system's state constraints, e.g., as given by lane boundaries for a self-driving vehicle. In this paper, we examine one commonly overlooked problem that arises in practical implementations of continuous-time CBF-based safety filters. In particular, we look at the issues caused by discrete-time implementations of the continuous-time CBF-based safety filter, especially for cases where the magnitude of the Lie derivative of the CBF with respect to the control input is zero or close to zero. When overlooked, this filter can result in undesirable chattering effects or constraint violations. In this work, we propose three mitigation strategies that allow us to use a continuous-time safety filter in a discrete-time implementation with a local relative degree. Using these strategies in augmented CBF-based safety filters, we achieve safety for all states in the safe set by either using an additional penalty term in the safety filtering objective or modifying the CBF such that those undesired states are not encountered during closed-loop operation. We demonstrate the presented issue and validate our three proposed mitigation strategies in simulation and on a real-world quadrotor.

关键词： Filters Prevention and mitigation Transforms Switches Reinforcement learning Control systems Safety

ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shen, Yanqing Tuna, Turcan Hutter, Marco Cadena, Cesar Zheng, Nanning Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China Robotic Systems Lab ETH Zurich Switzerland

Place recognition is essential to maintain global consistency in large-scale localization systems. While research in urban environments has progressed significantly using LiDARs or cameras, applications in natural forest-like environments remain largely under-explored. Furthermore, forests present particular challenges due to high self-similarity and substantial variations in vegetation growth over time. In this work, we propose a robust LiDAR-based place recognition method for natural forests, ForestLPR. We hypothesize that a set of cross-sectional images of the forest’s geometry at different heights contains the information needed to recognize revisiting a place. The cross-sectional images are represented by bird’s-eye view (BEV) density images of horizontal slices of the point cloud at different heights. Our approach utilizes a visual transformer as the shared backbone to produce sets of local descriptors and introduces a multi-BEV interaction module to attend to information at different heights adaptively. It is followed by an aggregation layer that produces a rotation-invariant place descriptor. We evaluated the efficacy of our method extensively on real-world data from public benchmarks as well as robotic datasets and compared it against the state-of-the-art (SOTA) methods. The results indicate that ForestLPR has consistently good performance on all evaluations and achieves an average increase of 7.38% and 9.11% on Recall@1 over the closest competitor on intra-sequence loop closure detection and inter-sequence re-localization, respectively, validating our hypothesis1 Copyright © 2025, The Authors. All rights reserved.

关键词： Forest ecology