IEEE Transactions on Robotics最新文献_第10页

Augmented Maximum Correntropy Criterion for Robust Geometric Perception 用于稳健几何感知的增量最大熵标准

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-21 DOI: 10.1109/TRO.2024.3484608

Jiayuan Li;Qingwu Hu;Xinyi Liu;Yongjun Zhang

{"title":"Augmented Maximum Correntropy Criterion for Robust Geometric Perception","authors":"Jiayuan Li;Qingwu Hu;Xinyi Liu;Yongjun Zhang","doi":"10.1109/TRO.2024.3484608","DOIUrl":"10.1109/TRO.2024.3484608","url":null,"abstract":"Maximum correntropy criterion (MCC) is a robust and powerful technique to handle heavy-tailed nonGaussian noise, which has many applications in the fields of vision, signal processing, machine learning, etc. In this article, we introduce several contributions to the MCC and propose an augmented MCC (AMCC), which raises the robustness of classic MCC variants for robust fitting to an unprecedented level. Our first contribution is to present an accurate bandwidth estimation algorithm based on the probability density function (PDF) matching, which solves the instability problem of the Silverman's rule. Our second contribution is to introduce the idea of graduated nonconvexity (GNC) and a worst-rejection strategy into MCC, which compensates for the sensitivity of MCC to high outlier ratios. Our third contribution is to provide a definition of local distribution measure to evaluate the quality of inliers, which makes the MCC no longer limited to random outliers but is generally suitable for both random and clustered outliers. Our fourth contribution is to show the generalizability of the proposed AMCC by providing eight application examples in geometry perception and performing comprehensive evaluations on five of them. Our experiments demonstrate that 1) AMCC is empirically robust to 80%\u0000<inline-formula><tex-math>$-$</tex-math></inline-formula>\u000090% of random outliers across applications, which is much better than Cauchy M-estimation, MCC, and GNC-GM; 2) AMCC achieves excellent performance in clustered outliers, whose success rate is 60%\u0000<inline-formula><tex-math>$-$</tex-math></inline-formula>\u000070% percentage points higher than the second-ranked method at 80% of outliers; 3) AMCC can run in real-time, which is 10\u0000<inline-formula><tex-math>$-$</tex-math></inline-formula>\u0000100 times faster than RANSAC-type methods in low-dimensional estimation problems with high outlier ratios. This gap will increase exponentially with the model dimension.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"40 ","pages":"4705-4724"},"PeriodicalIF":9.4,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142486814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Black-Box Physics-Informed Estimator Based on Gaussian Process Regression for Robot Inverse Dynamics Identification 基于高斯过程回归的黑盒物理信息估计器，用于机器人反动力学识别

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-07 DOI: 10.1109/TRO.2024.3474851

Giulio Giacomuzzo;Ruggero Carli;Diego Romeres;Alberto Dalla Libera

{"title":"A Black-Box Physics-Informed Estimator Based on Gaussian Process Regression for Robot Inverse Dynamics Identification","authors":"Giulio Giacomuzzo;Ruggero Carli;Diego Romeres;Alberto Dalla Libera","doi":"10.1109/TRO.2024.3474851","DOIUrl":"10.1109/TRO.2024.3474851","url":null,"abstract":"Learning the inverse dynamics of robots directly from data, adopting a black-box approach, is interesting for several real-world scenarios where limited knowledge about the system is available. In this article, we propose a black-box model based on Gaussian process (GP) regression for the identification of the inverse dynamics of robotic manipulators. The proposed model relies on a novel multidimensional kernel, called \u0000<italic>Lagrangian Inspired Polynomial\u0000 (LIP) kernel. The LIP kernel is based on two main ideas. First, instead of directly modeling the inverse dynamics components, we model as GPs the kinetic and potential energy of the system. The GP prior on the inverse dynamics components is derived from those on the energies by applying the properties of GPs under linear operators. Second, as regards the energy prior definition, we prove a polynomial structure of the kinetic and potential energy, and we derive a polynomial kernel that encodes this property. As a consequence, the proposed model allows also to estimate the kinetic and potential energy without requiring any label on these quantities. Results on simulation and on two real robotic manipulators, namely a 7 DOF Franka Emika Panda, and a 6 DOF MELFA RV4FL, show that the proposed model outperforms state-of-the-art black-box estimators based both on Gaussian processes and neural networks in terms of accuracy, generality, and data efficiency. The experiments on the MELFA robot also demonstrate that our approach achieves performance comparable to fine-tuned model-based estimators, despite requiring less prior information. The code of the proposed model is publicly available.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"40 ","pages":"4842-4858"},"PeriodicalIF":9.4,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142384280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Active Iterative Optimization for Aerial Visual Reconstruction of Wide-Area Natural Environment 用于广域自然环境航空视觉重建的主动迭代优化技术

IF 7.8 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-07 DOI: 10.1109/tro.2024.3475213

Hongpeng Wang, Zhongzhi Cao, Yue Fei, Peizhao Wang, Yaojing Li, Chuanyu Sun, Ming He, Jianda Han

引用次数: 0

Approximate Methods for Visibility-Based Pursuit–Evasion 基于可见度的追逐-入侵近似方法

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-04 DOI: 10.1109/TRO.2024.3474948

Emmanuel Antonio;Israel Becerra;Rafael Murrieta-Cid

{"title":"Approximate Methods for Visibility-Based Pursuit–Evasion","authors":"Emmanuel Antonio;Israel Becerra;Rafael Murrieta-Cid","doi":"10.1109/TRO.2024.3474948","DOIUrl":"10.1109/TRO.2024.3474948","url":null,"abstract":"To the best of our knowledge, an exact solution to the visibility-based pursuit–evasion problem with point agents and polygonal obstacles addressed in this work is not known. Given the above, in this work, we present approximate algorithms, but feasible and with other desirable properties, for such a pursuit–evasion game. Our new method combines asymptotically optimal motion planning based on sampling (more specifically, optimal probabilistic roadmaps) and the value iteration of dynamic programming. In addition, our formulation finds solutions for the evader when there are singular surfaces, which previous work could not find. In this work, we obtain two main theoretical results. We first prove that the proposed discrete formulation is correct (that the method obtains the solution for the discretization of the given configuration space). Subsequently, combining random graph results, Bellman's optimality principle, and limits, it is proved that, as the number of samples tends to infinity, our approximate discrete formulation becomes the continuous formulation corresponding to the Hamilton–Jacobi–Isaacs equation. This results in a feasible method that improves its approximation as the number of samples increases. Simulation experiments in 2-D and 3-D environments with obstacles that are simply and multiplicattively connected exemplify the results of the new method and show the advantages over previous work.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"40 ","pages":"4768-4786"},"PeriodicalIF":9.4,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Topology-Driven Parallel Trajectory Optimization in Dynamic Environments 动态环境中拓扑驱动的并行轨迹优化

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-04 DOI: 10.1109/TRO.2024.3475047

Oscar de Groot;Laura Ferranti;Dariu M. Gavrila;Javier Alonso-Mora

{"title":"Topology-Driven Parallel Trajectory Optimization in Dynamic Environments","authors":"Oscar de Groot;Laura Ferranti;Dariu M. Gavrila;Javier Alonso-Mora","doi":"10.1109/TRO.2024.3475047","DOIUrl":"10.1109/TRO.2024.3475047","url":null,"abstract":"Ground robots navigating in complex, dynamic environments must compute collision-free trajectories to avoid obstacles safely and efficiently. Nonconvex optimization is a popular method to compute a trajectory in real time. However, these methods often converge to locally optimal solutions and frequently switch between different local minima, leading to inefficient and unsafe robot motion. In this work, we propose a novel topology-driven trajectory optimization strategy for dynamic environments that plans multiple distinct evasive trajectories to enhance the robot's behavior and efficiency. A global planner iteratively generates trajectories in distinct homotopy classes. These trajectories are then optimized by local planners working in parallel. While each planner shares the same navigation objectives, they are locally constrained to a specific homotopy class, meaning each local planner attempts a different evasive maneuver. The robot then executes the feasible trajectory with the lowest cost in a receding horizon manner. We demonstrate on a mobile robot navigating among pedestrians that our approach leads to faster trajectories than existing planners.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"110-126"},"PeriodicalIF":9.4,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MAGICVFM-Meta-Learning Adaptation for Ground Interaction Control With Visual Foundation Models MAGICVFM - 利用可视地基模型进行地面交互控制的元学习适配

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-04 DOI: 10.1109/TRO.2024.3475212

Elena Sorina Lupu;Fengze Xie;James Alan Preiss;Jedidiah Alindogan;Matthew Anderson;Soon-Jo Chung

{"title":"MAGICVFM-Meta-Learning Adaptation for Ground Interaction Control With Visual Foundation Models","authors":"Elena Sorina Lupu;Fengze Xie;James Alan Preiss;Jedidiah Alindogan;Matthew Anderson;Soon-Jo Chung","doi":"10.1109/TRO.2024.3475212","DOIUrl":"10.1109/TRO.2024.3475212","url":null,"abstract":"Control of off-road vehicles is challenging due to the complex dynamic interactions with the terrain. Accurate modeling of these interactions is important to optimize driving performance, but the relevant physical phenomena, such as slip, are too complex to model from first principles. Therefore, we present an offline meta-learning algorithm to construct a rapidly-tunable model of residual dynamics and disturbances. Our model processes terrain images into features using a visual foundation model (VFM), then maps these features and the vehicle state to an estimate of the current actuation matrix using a deep neural network (DNN). We then combine this model with composite adaptive control to modify the last layer of the DNN in real time, accounting for the remaining terrain interactions not captured during offline training. We provide mathematical guarantees of stability and robustness for our controller, and demonstrate the effectiveness of our method through simulations and hardware experiments with a tracked vehicle and a car-like robot. We evaluate our method outdoors on different slopes with varying slippage and actuator degradation disturbances, and compare against an adaptive controller that does not use the VFM terrain features. We show significant improvement over the baseline in both hardware experimentation and simulation.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"180-199"},"PeriodicalIF":9.4,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On Semidefinite Relaxations for Matrix-Weighted State-Estimation Problems in Robotics 论机器人学中矩阵加权状态估计问题的半无限放松

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-04 DOI: 10.1109/TRO.2024.3475220

Connor Holmes;Frederike Dümbgen;Timothy Barfoot

{"title":"On Semidefinite Relaxations for Matrix-Weighted State-Estimation Problems in Robotics","authors":"Connor Holmes;Frederike Dümbgen;Timothy Barfoot","doi":"10.1109/TRO.2024.3475220","DOIUrl":"10.1109/TRO.2024.3475220","url":null,"abstract":"In recent years, there has been remarkable progress in the development of so-called \u0000<italic>certifiable perception\u0000 methods, which leverage semidefinite, convex relaxations to find \u0000<italic>global optima\u0000 of perception problems in robotics. However, many of these relaxations rely on simplifying assumptions that facilitate the problem formulation, such as an \u0000<italic>isotropic\u0000 measurement noise distribution. In this article, we explore the tightness of the semidefinite relaxations of \u0000<italic>matrix-weighted\u0000 (anisotropic) state-estimation problems and reveal the limitations lurking therein: matrix-weighted factors can cause convex relaxations to lose tightness. In particular, we show that the semidefinite relaxations of localization problems with matrix weights may be tight only for low noise levels. To better understand this issue, we introduce a theoretical connection between the posterior uncertainty of the state estimate and the certificate matrix obtained via convex relaxation. With this connection in mind, we empirically explore the factors that contribute to this loss of tightness and demonstrate that \u0000<italic>redundant constraints\u0000 can be used to regain it. As a second technical contribution of this article, we show that the state-of-the-art relaxation of scalar-weighted simultaneous localization and mapping cannot be used when matrix weights are considered. We provide an alternate formulation and show that its semidefinite program relaxation is not tight (even for very low noise levels) unless specific \u0000<italic>redundant constraints\u0000 are used. We demonstrate the tightness of our formulations on both simulated and real-world data.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"40 ","pages":"4805-4824"},"PeriodicalIF":9.4,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Distributed Auction Algorithm for Task Assignment With Robot Coalitions 机器人联盟任务分配的分布式拍卖算法

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-04 DOI: 10.1109/TRO.2024.3475209

Ruiliang Deng;Rui Yan;Peinan Huang;Zongying Shi;Yisheng Zhong

{"title":"A Distributed Auction Algorithm for Task Assignment With Robot Coalitions","authors":"Ruiliang Deng;Rui Yan;Peinan Huang;Zongying Shi;Yisheng Zhong","doi":"10.1109/TRO.2024.3475209","DOIUrl":"10.1109/TRO.2024.3475209","url":null,"abstract":"This study addresses the task assignment problem with robot coalitions, as encountered in practical scenarios, such as multiplayer reach-avoid games. Unlike the classical assignment problem where a single robot performs each task, the problem considered here involves tasks that require execution by a robot coalition consisting of two robots. This task assignment problem is a special instance of 3-set packing problem, which is known to be nondeterministic polynomial time (NP)-hard. We introduce the concept of \u0000<inline-formula><tex-math>$epsilon$</tex-math></inline-formula>\u0000-coalition-competitive equilibrium (\u0000<inline-formula><tex-math>$epsilon$</tex-math></inline-formula>\u0000-CCE) to characterize a kind of approximate solution that offers guaranteed performance. A distributed auction algorithm is developed to find an \u0000<inline-formula><tex-math>$epsilon$</tex-math></inline-formula>\u0000-CCE within a finite number of iterations. In addition, several enhancements have been implemented to adapt the auction algorithm for practical applications where the task assignment problem may vary over time. Numerical simulations demonstrate that the distributed algorithm achieves satisfactory approximation quality.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"40 ","pages":"4787-4804"},"PeriodicalIF":9.4,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving the Collision Tolerance of High-Speed Industrial Robots via Impact-Aware Path Planning and Series Clutched Actuation 通过冲击感知路径规划和串联离合器驱动提高高速工业机器人的碰撞耐受性

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-10-04 DOI: 10.1109/TRO.2024.3475208

Frederik Ostyn;Bram Vanderborght;Guillaume Crevecoeur

{"title":"Improving the Collision Tolerance of High-Speed Industrial Robots via Impact-Aware Path Planning and Series Clutched Actuation","authors":"Frederik Ostyn;Bram Vanderborght;Guillaume Crevecoeur","doi":"10.1109/TRO.2024.3475208","DOIUrl":"10.1109/TRO.2024.3475208","url":null,"abstract":"Robots are more often deployed in unstructured or unpredictable environments. Particularly collisions at high speed can severely damage the drivetrains and joint bearings of robots. In order to avoid such collisions, path planners exist that adapt the robot's original trajectory online if a collision hazard is detected. These methods require additional sensors such as cameras, are computationally costly and never flawless due to occlusions. Another approach is to incorporate a cost function that promotes collision tolerance while planning the initial trajectory. The resulting impact-aware path plan minimizes the chance of robot hardware damage if a collision would occur. Two algorithms are presented to assess collision tolerance in high-speed robots, taking into account factors such as robot pose, impact direction, and maximum intermittent loading of the gearboxes and bearings. The first algorithm is more general while the second assumes the presence of joint overload clutches that decouple upon impact. These algorithms are applied to plan an impact-aware path for a custom 6-axis series clutched actuated robot that serves as use case. Both for the case with and without clutches, a generic impact-aware plan is presented as well as at least one derived, heuristic alternative. Without clutches, trajectories that are perpendicular to the end effector flange were found to be desirable, as they allow the robot to mitigate the highest collision force without overloading the gearboxes or bearings. On the other hand, with clutches, trajectories that are parallel to the end effector flange were found to be more collision tolerant. The effect of impact direction was also experimentally validated using the custom 6-axis robot. Collisions at velocities up to 1.2 m/s were mitigated through the combination of impact-aware path planning and series clutched actuation.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"40 ","pages":"4825-4841"},"PeriodicalIF":9.4,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning 利用隐式行为克隆和动态运动原型促进机器人运动规划的强化学习

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-09-26 DOI: 10.1109/TRO.2024.3468770

Zengjie Zhang;Jayden Hong;Amir M. Soufi Enayati;Homayoun Najjaran

{"title":"Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning","authors":"Zengjie Zhang;Jayden Hong;Amir M. Soufi Enayati;Homayoun Najjaran","doi":"10.1109/TRO.2024.3468770","DOIUrl":"10.1109/TRO.2024.3468770","url":null,"abstract":"Reinforcement learning (RL) for motion planning of multi-degree-of-freedom robots still suffers from low efficiency in terms of slow training speed and poor generalizability. In this article, we propose a novel RL-based robot motion planning framework that uses implicit behavior cloning (IBC) and dynamic movement primitive (DMP) to improve the training speed and generalizability of an off-policy RL agent. IBC utilizes human demonstration data to leverage the training speed of RL, and DMP serves as a heuristic model that transfers motion planning into a simpler planning space. To support this, we also create a human demonstration dataset using a pick-and-place experiment that can be used for similar studies. Comparison studies reveal the advantage of the proposed method over the conventional RL agents with faster training speed and higher scores. A real-robot experiment indicates the applicability of the proposed method to a simple assembly task. Our work provides a novel perspective on using motion primitives and human demonstration to leverage the performance of RL for robot applications.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"40 ","pages":"4733-4749"},"PeriodicalIF":9.4,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142325151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0