检索结果-内蒙古大学图书馆

Contact-Rich SE(3)-Equivariant robot Manipulation Task learning via Geometric Impedance control

IEEE robotICS AND AUTOMATION LETTERS 2024年第2期9卷 1508-1515页

作者： Seo, Joohwan Prakash, Nikhil P. S. Zhang, Xiang Wang, Changhao Choi, Jongeun Tomizuka, Masayoshi Horowitz, Roberto Univ Calif Berkeley Dept Mech Engn Berkeley CA 94720 USA Yonsei Univ Sch Mech Engn Seoul 03722 South Korea

This letter presents a differential geometric control approach that leverages SE(3) group invariance and equivariance to increase transferability in learning robot manipulation tasks that involve interaction with the environment. Specifically, we employ a control law and a learning representation framework that remain invariant under arbitrary SE(3) transformations of the manipulation task definition. Furthermore, the control law and learning representation framework are shown to be SE(3) equivariant when represented relative to the spatial frame. The proposed approach is based on utilizing a recently presented geometric impedance control (GIC) combined with a learning variable impedance control framework, where the gain scheduling policy is trained in a supervised learning fashion from expert demonstrations. A geometrically consistent error vector (GCEV) is fed to a neural network to achieve a gain scheduling policy that remains invariant to arbitrary translation and rotations. A comparison of our proposed control and learning framework with a well-known Cartesian space learning impedance control, equipped with a Cartesian error vector-based gain scheduling policy, confirms the significantly superior learning transferability of our proposed approach. A hardware implementation on a peg-in-hole task is conducted to validate the learning transferability and feasibility of the proposed approach.

关键词： machine learning for robot control compliance and impedance control learning from demonstration

来源：评论

学校读者我要写书评

暂无评论

Model Optimization in Deep learning Based robot control for Autonomous Driving

引用

IEEE robotICS AND AUTOMATION LETTERS 2024年第1期9卷 715-722页

作者： Paniego, Sergio Paliwal, Nikhil Canas, Jose Maria Univ Rey Juan Carlos Madrid 28933 Spain JdeRobot Org Madrid 28922 Spain Saarland Univ D-66123 Saarbrucken Germany

Deep learning (DL) has been successfully used in robotics for perception tasks and end-to-end robot control. In the context of autonomous driving, this work explores and compares a variety of alternatives for model optimization to solve the visual lane-follow application in urban scenarios with an imitation learning approach. The optimization techniques include quantization, pruning, fine-tuning (retraining), and clustering, covering all the options available at the most common DL frameworks. TensorRT optimization for specific cutting-edge hardware devices has been also explored. For the comparison, offline metrics such as mean squared error and inference time are used. In addition, the optimized models have been evaluated in an online fashion using the autonomous driving state-of-the-art simulator CARLA and an assessment tool called Behavior Metrics, which provides holistic quantitative fine-grain data about robot performance. Typically the performance of robot applications depends both on the quality of the control decisions and also on their frequency. The studied optimized models significantly increase inference frequency without losing decision quality. The impact of each optimization alone has also been measured. This speed-up allows us to successfully run DL robot-control applications even in limited computing hardware. All the work presented here is open-source, including models, weights, assessment tool, and dataset, for easy replication and extension.

关键词： Imitation learning machine learning for robot control sensorimotor learning

来源：评论

学校读者我要写书评

暂无评论

Sensorimotor learning With Stability Guarantees via Autonomous Neural Dynamic Policies

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第2期10卷 1760-1767页

作者： Totsila, Dionis Chatzilygeroudis, Konstantinos Modugno, Valerio Hadjivelichkov, Denis Kanoulas, Dimitrios Univ Lorraine Inria CNRS Loria F-54000 Nancy France Univ Patras Dept Math Computat Intelligence Lab CILab Patras 26504 Greece Univ Patras Dept Elect & Comp Engn Lab Automat & Robot LAR Patras 26504 Greece UCL Dept Comp Sci Robot Percept & Learning Lab RPL Lab London WC1E 6BT England Archimedes Athena RC Maroussi 15125 Greece

State-of-the-art sensorimotor learning algorithms, either in the context of reinforcement learning or imitation learning, offer policies that can often produce unstable behaviors, damaging the robot and/or the environment. Moreover, it is very difficult to interpret the optimized controller and analyze its behavior and/or performance. Traditional robot learning, on the contrary, relies on dynamical system-based policies that can be analyzed for stability/safety. Such policies, however, are neither flexible nor generic and usually work only with proprioceptive sensor states. In this work, we bridge the gap between generic neural network policies and dynamical system-based policies, and we introduce Autonomous Neural Dynamic Policies (ANDPs) that: (a) are based on autonomous dynamical systems, (b) always produce asymptotically stable behaviors, and (c) are more flexible than traditional stable dynamical system-based policies. ANDPs are fully differentiable, flexible generic-policies that accept any observation input, while ensuring asymptotic stability. Through several experiments, we explore the flexibility and capacity of ANDPs in several imitation learning tasks including experiments with image observations. The results show that ANDPs combine the benefits of both neural network-based and dynamical system-based methods.

关键词： robots Artificial neural networks Dynamical systems Stability analysis Asymptotic stability Aerospace electronics robot learning Imitation learning Trajectory Heuristic algorithms learning from demonstration machine learning for robot control sensorimotor learning

来源：评论

学校读者我要写书评

暂无评论

ALARM: Safe Reinforcement learning With Reliable Mimicry for Robust Legged Locomotion

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第7期10卷 6768-6775页

作者： Zhou, Qiqi Ding, Hui Chen, Teng Man, Luxin Jiang, Han Zhang, Guoteng Li, Bin Rong, Xuewen Li, Yibin Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China Qilu Univ Technol Shandong Acad Sci Sch Math & Stat Jinan 250353 Peoples R China

Legged robots are supposed to traverse complicated environments, which makes it challenging to design a model-based controller due to their functional complexity. Currently, using deep reinforcement learning to improve the adaptability of robots in complex scenarios has been a major research trend. In this letter, we propose Adaptive Latent Aggregation for Reliable Mimicry (ALARM), a reinforcement learning framework that enables safe and robust locomotion in legged robots using only proprioception. This work features a one-step teacher-student training paradigm by constructing an adaptive aggregation strategy, which integrates the merits of imitation learning and reinforcement learning effectively. The framework integrates normalized penalized proximal policy optimization, which penalizes constraint-violating behaviors while optimizing locomotion policy. Our method facilitates efficient sim-to-real transfer, offering a promising approach for real-world legged robot applications.

关键词： robots Legged locomotion Training Reliability Quadrupedal robots Sensors Costs Complexity theory Propioception Legged robots machine learning for robot control imitation learning reinforcement learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Certifiable Reachability learning Using a New Lipschitz Continuous Value Function

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第4期10卷 3582-3589页

作者： Li, Jingqi Lee, Donggun Lee, Jaewon Dong, Kris Shengjun Sojoudi, Somayeh Tomlin, Claire Univ Calif Berkeley Berkeley CA 94704 USA North Carolina State Univ Raleigh NC 27606 USA Boson AI Santa Clara CA 95054 USA

We propose a new reachability learning framework for high-dimensional nonlinear systems, focusing on reach-avoid problems. These problems require computing the reach-avoid set, which ensures that all its elements can safely reach a target set despite disturbances within pre-specified bounds. Our framework has two main parts: offline learning of a newly designed reach-avoid value function, and post-learning certification. Compared to prior work, our new value function is Lipschitz continuous and its associated Bellman operator is a contraction mapping, both of which improve the learning performance. To ensure deterministic guarantees of our learned reach-avoid set, we introduce two efficient post-learning certification methods. Both methods can be used online for real-time local certification or offline for comprehensive certification. We validate our framework in a 12-dimensional crazyflie drone racing hardware experiment and a simulated 10-dimensional highway take-over example.

关键词： Drones Certification Safety Logic gates Real-time systems Level set Reachability analysis Hardware Trajectory Reinforcement learning Reachability machine learning for robot control reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PIETRA: Physics-Informed Evidential learning for Traversing Out-of-Distribution Terrain

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第3期10卷 2359-2366页

作者： Cai, Xiaoyi Queeney, James Xu, Tong Datar, Aniket Pan, Chenhui Miller, Max Flather, Ashton Osteen, Philip R. Roy, Nicholas Xiao, Xuesu How, Jonathan P. MIT Cambridge MA 02139 USA Mitsubishi Elect Res Labs MERL Cambridge MA 02139 USA George Mason Univ Fairfax VA 22030 USA DEVCOM Army Res Lab Adelphi MD 20783 USA

Self-supervised learning is a powerful approach for developing traversability models for off-road navigation, but these models often struggle with inputs unseen during training. Existing methods utilize techniques like evidential deep learning to quantify model uncertainty, helping to identify and avoid out-of-distribution terrain. However, always avoiding out-of-distribution terrain can be overly conservative, e.g., when novel terrain can be effectively analyzed using a physics-based model. To overcome this challenge, we introduce Physics-Informed Evidential Traversability (PIETRA), a self-supervised learning framework that integrates physics priors directly into the mathematical formulation of evidential neural networks and introduces physics knowledge implicitly through an uncertainty-aware, physics-informed training loss. Our evidential network seamlessly transitions between learned and physics-based predictions for out-of-distribution inputs. Additionally, the physics-informed loss regularizes the learned model, ensuring better alignment with the physics model. Extensive simulations and hardware experiments demonstrate that PIETRA improves both learning accuracy and navigation performance in environments with significant distribution shifts.

关键词： Physics Navigation Data models Training Uncertainty robots Planning Analytical models Predictive models Mathematical models machine learning for robot control motion and path planning

来源：评论

学校读者我要写书评

暂无评论

π-MPPI: A Projection-Based Model Predictive Path Integral Scheme for Smooth Optimal control of Fixed-Wing Aerial Vehicles

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第6期10卷 6496-6503页

作者： Andrejev, Edvin Martin Manoharan, Amith Unt, Karl-Eerik Singh, Arun Kumar Univ Tartu Inst Technol EE-50411 Tartu Estonia Estonian Aviat Acad EE-61707 Tartu Estonia

Model Predictive Path Integral (MPPI) is a popular sampling-based Model Predictive control (MPC) algorithm for nonlinear systems. It optimizes trajectories by sampling control sequences and averaging them. However, a key issue with MPPI is the non-smoothness of the optimal control sequence, leading to oscillations in systems like fixed-wing aerial vehicles (FWVs). Existing solutions use post-hoc smoothing, which fails to bound control derivatives. This letter introduces a new approach: we add a projection filter pi to minimally correct control samples, ensuring bounds on control magnitude and higher-order derivatives. The filtered samples are then averaged using MPPI, leading to our pi-MPPI approach. We minimize computational overhead by using a neural accelerated custom optimizer for the projection filter. pi-MPPI offers a simple way to achieve arbitrary smoothness in control sequences. While we focus on FWVs, this projection filter can be integrated into any MPPI pipeline. Applied to FWVs, pi-MPPI is easier to tune than the baseline, resulting in smoother, more robust performance.

关键词： Trajectory Optimal control Costs Vectors Stacking Smoothing methods Filtering algorithms Tuning Training Noise Optimization and optimal control aerial systems: Mechanics and control machine learning for robot control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Exploration With Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第6期10卷 6143-6150页

作者： Le, Huy Hoang, Tai Gabriel, Miroslav Neumann, Gerhard Vien, Ngo Anh Bosch Ctr Artificial Intelligence D-71272 Renningen Germany Karlsruhe Inst Technol Inst Anthropomat & Robot D-76131 Karlsruhe Germany

learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid framework that tackles both discrete and continuous action spaces. First, we model the continuous motion parameter policy as a diffusion model, and second, we incorporate this into a maximum entropy reinforcement learning framework that unifies both the discrete and continuous components. The discrete action space, such as contact point selection, is optimized through Q-value function maximization, while the continuous part is guided by a diffusion-based policy. This hybrid approach leads to a principled objective, where the maximum entropy term is derived as a lower bound using structured variational inference. We propose the Hybrid Diffusion Policy algorithm (HyDo) and evaluate its performance on both simulation and zero-shot sim2real tasks. Our results show that HyDo encourages more diverse behavior policies, leading to significantly improved success rates across tasks - for example, increasing from 53% to 72% on a real-world 6D pose alignment task.

关键词： Entropy Diffusion models Training robots Lower bound Complexity theory Q-learning Inference algorithms Imitation learning Service robots Reinforcement learning machine learning for robot control dexterous manipulation

来源：评论

学校读者我要写书评

暂无评论

QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-learning

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第1期10卷 112-119页

作者： Kotb, Mostafa Weber, Cornelius Hafez, Muhammad Burhan Wermter, Stefan Univ Hamburg Dept Informat Knowledge Technol Grp D-22527 Hamburg Germany Aswan Univ Fac Sci Math Dept Aswan 81528 Egypt Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ England

Inspired by the success of the Transformer architecture in natural language processing and computer vision, we investigate the use of Transformers in Reinforcement learning (RL), specifically in modeling the environment's dynamics using Transformer Dynamics Models (TDMs). We evaluate the capabilities of TDMs for continuous control in real-time planning scenarios with Model Predictive control (MPC). While Transformers excel in long-horizon prediction, their tokenization mechanism and autoregressive nature lead to costly planning over long horizons, especially as the environment's dimensionality increases. To alleviate this issue, we use a TDM for short-term planning, and learn an autoregressive discrete Q-function using a separate Q-Transformer (QT) model to estimate a long-term return beyond the short-horizon planning. Our proposed method, QT-TDM, integrates the robust predictive capabilities of Transformers as dynamics models with the efficacy of a model-free Q-Transformer to mitigate the computational burden associated with real-time planning. Experiments in diverse state-based continuous control tasks show that QT-TDM is superior in performance and sample efficiency compared to existing Transformer-based RL models while achieving fast and computationally efficient inference.

关键词： Model learning for control machine learning for robot control deep learning methods Model learning for control machine learning for robot control deep learning methods

来源：评论

学校读者我要写书评

暂无评论

Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial robots

引用

IEEE robotICS AND AUTOMATION LETTERS 2025年第4期10卷 4093-4100页

作者： Kulkarni, Mihir Rehberg, Welf Alexis, Kostas Norwegian Univ Sci & Technol Dept Engn Cybernet OS Bragstads Plass 2D N-7034 Trondheim Norway

This paper contributes the Aerial Gym Simulator, a highly parallelized, modular framework for simulation and rendering of arbitrary multirotor platforms based on NVIDIA Isaac Gym. Aerial Gym supports the simulation of under-, fully- and over-actuated multirotors offering parallelized geometric controllers, alongside a custom GPU-accelerated rendering framework for ray-casting capable of capturing depth, segmentation and vertex-level annotations from the environment. Multiple examples for key tasks, such as depth-based navigation through reinforcement learning are provided. The comprehensive set of tools developed within the framework makes it a powerful resource for research on learning for control, planning, and navigation using state information as well as exteroceptive sensor observations. Extensive simulation studies are conducted and successful sim2real transfer of trained policies is demonstrated.

关键词： robots robot sensing systems Rendering (computer graphics) Physics Engines Navigation Training Motors Planning Autonomous aerial vehicles Aerial Systems: perception and autonomy machine learning for robot control reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：