检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jose, Allen Isaac Pan, Sicong Zaenker, Tobias Menon, Rohit Houben, Sebastian Bennewitz, Maren Bonn-Rhein-Sieg University of Applied Sciences Germany Humanoid Robots Lab University of Bonn Germany Fraunhofer Institute for Intelligent Analysis and Information Systems Germany Humanoid Robots Lab University of Bonn Lamarr Institute for Machine Learning and Artificial Intelligence Center for Robotics University of Bonn Germany

Automating labor-intensive tasks such as crop monitoring with robots is essential for enhancing production and conserving resources. However, autonomously monitoring horticulture crops remains challenging due to their complex structures, which often result in fruit occlusions. Existing view planning methods attempt to reduce occlusions but either struggle to achieve adequate coverage or incur high robot motion costs. We introduce a global optimization approach for view motion planning that aims to minimize robot motion costs while maximizing fruit coverage. To this end, we leverage coverage constraints derived from the set covering problem (SCP) within a shortest Hamiltonian path problem (SHPP) formulation. While both SCP and SHPP are well-established, their tailored integration enables a unified framework that computes a global view path with minimized motion while ensuring full coverage of selected targets. Given the NP-hard nature of the problem, we employ a region-prior-based selection of coverage targets and a sparse graph structure to achieve effective optimization outcomes within a limited time. Experiments in simulation demonstrate that our method detects more fruits, enhances surface coverage, and achieves higher volume accuracy than the motion-efficient baseline with a moderate increase in motion cost, while significantly reducing motion costs compared to the coverage-focused baseline. Real-world experiments further confirm the practical applicability of our approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised learning of Scene-Graph Representations for Robotic Sequential Manipulation Planning 4

Self-Supervised Learning of Scene-Graph Representations for ...

引用

4th Conference on Robot learning, CoRL 2020

作者： Nguyen, Son-Tung Oguz, Ozgur S. Hartmann, Valentin N. Toussaint, Marc Machine Learning & Robotics Lab University of Stuttgart Germany Max Planck Institute for Intelligent Systems Germany Learning and Intelligent Systems Group TU Berlin Germany

We present a self-supervised representation learning approach for visual reasoning and integrate it into a nonlinear program formulation for motion optimization to tackle sequential manipulation tasks. Such problems have usually been addressed by combined task and motion planning approaches, for which spatial relations and logical rules that rely on symbolic representations have to be predefined by the user. We propose to learn relational structures by leveraging visual perception to alleviate the resulting knowledge acquisition bottleneck. In particular, we learn constructing scene-graphs, that represent objects ("red box"), and their spatial relationships ("yellow cylinder on red box"). This representation allows us to plan high-level discrete decisions effectively using graph search algorithms. We integrate the visual reasoning module with a nonlinear optimization method for robot motion planning and verify its feasibility on the classic blocks-world domain. Our proposed framework successfully finds the sequence of actions and enables the robot to execute feasible motion plans to realize the given tasks. © 2020 Proceedings of Machine learning Research. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

learning to execute: efficiently learning universal plan-conditioned policies in robotics 21

Learning to execute: efficiently learning universal plan-con...

引用

Proceedings of the 35th International Conference on Neural Information Processing systems

作者： Ingmar Schubert Danny Driess Ozgur S. Oguz Marc Toussaint Learning and Intelligent Systems Group TU Berlin Germany Machine Learning and Robotics Lab University of Stuttgart Germany

ISBN: (纸本)9781713845393

Applications of Reinforcement learning (RL) in robotics are often limited by high data demand. On the other hand, approximate models are readily available in many robotics scenarios, making model-based approaches like planning a data-efficient alternative. Still, the performance of these methods suffers if the model is imprecise or wrong. In this sense, the respective strengths and weaknesses of RL and model-based planners are complementary. In the present work, we investigate how both approaches can be integrated into one framework that combines their strengths. We introduce learning to Execute (L2E), which leverages information contained in approximate plans to learn universal policies that are conditioned on plans. In our robotic manipulation experiments, L2E exhibits increased performance when compared to pure RL, pure planning, or baseline methods combining learning and planning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

learning to execute: Efficiently learning universal plan-conditioned policies in robotics

arXiv

引用

arXiv 2021年

作者： Schubert, Ingmar Driess, Danny Oguz, Ozgur S. Toussaint, Marc Learning and Intelligent Systems Group Tu Berlin Germany Machine Learning and Robotics Lab University of Stuttgart Germany

Applications of Reinforcement learning (RL) in robotics are often limited by high data demand. On the other hand, approximate models are readily available in many robotics scenarios, making model-based approaches like planning a data-efficient alternative. Still, the performance of these methods suffers if the model is imprecise or wrong. In this sense, the respective strengths and weaknesses of RL and modelbased planners are complementary. In the present work, we investigate how both approaches can be integrated into one framework that combines their strengths. We introduce learning to Execute (L2E), which leverages information contained in approximate plans to learn universal policies that are conditioned on plans. In our robotic manipulation experiments, L2E exhibits increased performance when compared to pure RL, pure planning, or baseline methods combining learning and planning. © 2021, CC BY.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Co-Optimizing Robot, Environment, and Tool Design via Joint Manipulation Planning

Co-Optimizing Robot, Environment, and Tool Design via Joint ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Marc Toussaint Jung-Su Ha Ozgur S. Oguz Learning & Intelligent Systems Lab TU Berlin Germany Max Planck Institute for Intelligent Systems Germany Machine Learning & Robotics Lab University of Stuttgart Germany

Existing work on sequential manipulation planning and trajectory optimization typically assumes the robot, environment and tools to be given. However, in particular in industrial applications, it is highly interesting to ask, what would be an optimal robot design, tool shape, or robot station geometry for a particular ensemble of manipulation tasks. To tackle this problem we propose a formulation to jointly optimize over static design parameters and the sequential manipulation trajectory. We can include optimization objectives such as penalizing velocities (path length) and joint torques. Our evaluations show that design optimization can significantly improve on such metrics. For instance, in a wrench tool demonstration scenario we show that the shape of the wrench tool as well as design of the robot can be optimized to allow for exerting a necessary external torque with minimal effort.

关键词： Measurement Torque Service robots Shape Tools Programming Planning

来源：评论

学校读者我要写书评

暂无评论

learning Efficient Constraint Graph Sampling for Robotic Sequential Manipulation

Learning Efficient Constraint Graph Sampling for Robotic Seq...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Joaquim Ortiz-Haro Valentin N. Hartmann Ozgur S. Oguz Marc Toussaint Machine Learning & Robotics Lab University of Stuttgart Germany Learning and Intelligent Systems Lab TU Berlin Germany Max Planck Institute for Intelligent Systems Germany

Efficient sampling from constraint manifolds, and thereby generating a diverse set of solutions for feasibility problems, is a fundamental challenge. We consider the case where a problem is factored, that is, the underlying nonlinear program is decomposed into differentiable equality and inequality constraints, each of which depends only on some variables. Such problems are at the core of efficient and robust sequential robot manipulation planning. Naive sequential conditional sampling of individual variables, as well as fully joint sampling of all variables at once (e.g., leveraging optimization methods), can be highly inefficient and non-robust. We propose a novel framework to learn how to break the overall problem into smaller sequential sampling problems. Specifically, we leverage Monte-Carlo Tree Search to learn assignment orders for the variable-subsets, in order to minimize the computation time to generate feasible full samples. This strategy allows us to efficiently compute a set of diverse valid robot configurations for mode-switches within sequential manipulation tasks, which are waypoints for subsequent trajectory optimization or sampling-based motion planning algorithms. We show that the learning method quickly converges to the best sampling strategy for a given problem, and outperforms user-defined orderings or fully joint optimization, while providing a higher sample diversity. Video: https://***/mCNdvjTbHNI

关键词： Manifolds learning systems Costs Monte Carlo methods Conferences Optimization methods Planning

来源：评论

学校读者我要写书评

暂无评论

Deep 6-DoF Tracking of Unknown Objects for Reactive Grasping

Deep 6-DoF Tracking of Unknown Objects for Reactive Grasping

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Marc Tuscher Julian Hörz Danny Driess Marc Toussaint sereact Machine Learning and Robotics Lab University of Stuttgart Max-Planck Institute for Intelligent Systems Stuttgart Learning and Intelligent Systems TU Berlin

Robotic manipulation of unknown objects is an important field of research. Practical applications occur in many real-world settings where robots need to interact with an unknown environment. We tackle the problem of reactive grasping by proposing a method for unknown object tracking, grasp point sampling and dynamic trajectory planning. Our object tracking method combines Siamese Networks with an Iterative Closest Point approach for pointcloud registration into a method for 6-DoF unknown object tracking. The method does not require further training and is robust to noise and occlusion. We propose a robotic manipulation system, which is able to grasp a wide variety of formerly unseen objects and is robust against object perturbations and inferior grasping points.

关键词： Training Target tracking Automation Trajectory planning Perturbation methods Conferences Grasping

来源：评论

学校读者我要写书评

暂无评论

Preventing Unconstrained CBF Safety Filters Caused by Invalid Relative Degree Assumptions

arXiv

引用

arXiv 2024年

作者： Brunke, Lukas Zhou, Siqi Schoellig, Angela P. Learning Systems and Robotics Lab The Munich Institute of Robotics and Machine Intelligence Technical University of Munich Munich80333 Germany University of Toronto Institute for Aerospace Studies North YorkONM3H 5T6 Canada University of Toronto Robotics Institute TorontoONM5S 1A4 Canada Vector Institute for Artificial Intelligence TorontoONM5G 0C6 Canada

Control barrier function (CBF)-based safety filters are used to certify and modify potentially unsafe control inputs to a system such as those provided by a reinforcement learning agent or a non-expert user. In this context, safety is defined as the satisfaction of state constraints. Originally designed for continuous-time systems, CBF safety filters typically assume that the system’s relative degree is well-defined and is constant across the domain;however, this assumption is restrictive and rarely verified—even linear system dynamics with a quadratic CBF candidate may not satisfy this assumption. In real-world applications, continuous-time CBF safety filters are implemented in discrete time, exacerbating issues related to violating the condition on the relative degree. These violations can lead to the safety filter being unconstrained (any control input may be certified) for a finite time interval and result in chattering issues and constraint violations. We propose an alternative formulation to address these challenges. Specifically, we present a theoretically sound method that employs multiple CBFs to generate bounded control inputs at each state within the safe set, thereby preventing incorrect certification of arbitrary control inputs. Using this approach, we derive conditions on the maximum sampling time to ensure safety in discrete-time implementations. We demonstrate the effectiveness of our proposed method through simulations and real-world quadrotor experiments, successfully preventing chattering and constraint violations. Finally, we discuss the implications of violating the relative degree condition on CBF synthesis and learning-based CBF methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Context-Based Meta Reinforcement learning for Robust and Adaptable Peg-in-Hole Assembly Tasks

arXiv

引用

arXiv 2024年

作者： Shokry, Ahmed Gomaa, Walid Zaenker, Tobias Dawood, Murad Maged, Shady A. Awad, Mohammed I. Bennewitz, Maren Humanoid Robots Lab University of Bonn the Center for Robotics Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Bonn Germany Cyber Physical Systems Lab Egypt Japan University of Science and Technology Alexandria Egypt Faculty of Engineering Alexandria University Alexandria Egypt Mechatronics Department Ain Shams University Cairo Egypt

Peg-in-hole assembly in unknown environments is a challenging task due to onboard sensor errors, which result in uncertainty and variations in task parameters such as the hole position and orientation. Meta Reinforcement learning (Meta RL) has been proposed to mitigate this problem as it learns how to quickly adapt to new tasks with different parameters. However, previous approaches either depend on a sample-inefficient procedure or human demonstrations to perform the task in the real world. Our work modifies the data used by the Meta RL agent and uses simple features that can be easily measured in the real world even with an uncalibrated camera. We further adapt the Meta RL agent to use data from a force/torque sensor, instead of the camera, to perform the assembly, using a small amount of training data. Finally, we propose a fine-tuning method that consistently and safely adapts to out-of-distribution tasks with parameters that differ by a factor of 10 from the training tasks. Our results demonstrate that the proposed data modification significantly enhances the training and adaptation efficiency and enables the agent to achieve 100% success in tasks with different hole positions and orientations. Experiments on a real robot confirm that both camera- and force/torque sensor-equipped agents achieve 100% success in tasks with unknown hole positions, matching their simulation performance and validating the approach’s robustness and applicability. Compared to the previous work with sample-inefficient adaptation, our proposed methods are 10 times more sample-efficient in the real-world tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Semantically Safe Robot Manipulation: From Semantic Scene Understanding to Motion Safeguards

arXiv

引用

arXiv 2024年

作者： Brunke, Lukas Zhang, Yanni Römer, Ralf Naimer, Jack Staykov, Nikola Zhou, Siqi Schoellig, Angela P. The Learning Systems and Robotics Lab The Munich Institute of Robotics and Machine Intelligence Technical University of Munich Munich80333 Germany University of Toronto Institute for Aerospace Studies North YorkONM3H 5T6 Canada University of Toronto Robotics Institute TorontoONM5S 1A4 Canada Vector Institute for Artificial Intelligence TorontoONM5G 0C6 Canada

Ensuring safe interactions in human-centric environments requires robots to understand and adhere to constraints recognized by humans as "common sense" (e.g., "moving a cup of water above a laptop is unsafe as the water may spill" or "rotating a cup of water is unsafe as it can lead to pouring its content"). Recent advances in computer vision and machine learning have enabled robots to acquire a semantic understanding of and reason about their operating environments. While extensive literature on safe robot decision-making exists, semantic understanding is rarely integrated into these formulations. In this work, we propose a semantic safety filter framework to certify robot inputs with respect to semantically defined constraints (e.g., unsafe spatial relationships, behaviours, and poses) and geometrically defined constraints (e.g., environment-collision and self-collision constraints). In our proposed approach, given perception inputs, we build a semantic map of the 3D environment and leverage the contextual reasoning capabilities of large language models to infer semantically unsafe conditions. These semantically unsafe conditions are then mapped to safe actions through a control barrier certification formulation. We evaluated our semantic safety filter approach in teleoperated tabletop manipulation tasks and pick-and-place tasks, demonstrating its effectiveness in incorporating semantic constraints to ensure safe robot operation beyond collision avoidance. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

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：