检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation (ICRA)

作者： Jung-Su Ha Danny Driess Marc Toussaint Machine Learning & Robotics Lab University Stuttgart and with the Max Planck Institute for Intelligent Systems Stuttgart Germany

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Logic-Geometric Programming (LGP) is a powerful motion and manipulation planning framework, which represents hierarchical structure using logic rules that describe discrete aspects of problems, e.g., touch, grasp, hit, or push, and solves the resulting smooth trajectory optimization. The expressive power of logic allows LGP for handling complex, large-scale sequential manipulation and tool-use planning problems. In this paper, we extend the LGP formulation to stochastic domains. Based on the control-inference duality, we interpret LGP in a stochastic domain as fitting a mixture of Gaussians to the posterior path distribution, where each logic pro le defines a single Gaussian path distribution. The proposed framework enables a robot to prioritize various interaction modes and to acquire interesting behaviors such as contact exploitation for uncertainty reduction, eventually providing a composite control scheme that is reactive to disturbance.

关键词： Robots Planning Trajectory optimization Skeleton Programming

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Framework for Constrained Manipulations and Task and Motion Planning under Uncertainty

arXiv

引用

arXiv 2020年

作者： Ha, Jung-Su Driess, Danny Toussaint, Marc Machine Learning & Robotics Lab University Stuttgart Max Planck Institute for Intelligent Systems Stuttgart Germany

— Logic-Geometric Programming (LGP) is a powerful motion and manipulation planning framework, which represents hierarchical structure using logic rules that describe discrete aspects of problems, e.g., touch, grasp, hit, or push, and solves the resulting smooth trajectory optimization. The expressive power of logic allows LGP for handling complex, large-scale sequential manipulation and tool-use planning problems. In this paper, we extend the LGP formulation to stochastic domains. Based on the control-inference duality, we interpret LGP in a stochastic domain as fitting a mixture of Gaussians to the posterior path distribution, where each logic profile defines a single Gaussian path distribution. The proposed framework enables a robot to prioritize various interaction modes and to acquire interesting behaviors such as contact exploitation for uncertainty reduction, eventually providing a composite control scheme that is reactive to disturbance. The supplementray video can be found at https://***/CEaJdVlSZyo. Copyright © 2020, The Authors. 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

Robot programming from demonstration, feedback and transfer

Robot programming from demonstration, feedback and transfer

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Y. Mollard T. Munzer A. Baisero M. Toussaint M. Lopes Flowers Team Inria France Machine Learning and Robotics Lab University of Stuttgart Germany

This paper presents a novel approach for robot instruction for assembly tasks. We consider that robot programming can be made more efficient, precise and intuitive if we leverage the advantages of complementary approaches such as learning from demonstration, learning from feedback and knowledge transfer. Starting from low-level demonstrations of assembly tasks, the system is able to extract a high-level relational plan of the task. A graphical user interface (GUI) allows then the user to iteratively correct the acquired knowledge by refining high-level plans, and low-level geometrical knowledge of the task. This combination leads to a faster programming phase, more precise than just demonstrations, and more intuitive than just through a GUI. A final process allows to reuse high-level task knowledge for similar tasks in a transfer learning fashion. Finally we present a user study illustrating the advantages of this approach.

关键词： Assembly Graphical user interfaces Service robots Computational modeling Context Training

来源：评论

学校读者我要写书评

暂无评论

ST-RRT*: Asymptotically-Optimal Bidirectional Motion Planning through Space-Time

arXiv

引用

arXiv 2022年

作者： Grothe, Francesco Hartmann, Valentin N. Orthey, Andreas Toussaint, Marc Learning and Intelligent Systems Group TU Berlin Germany Machine Learning & Robotics Lab University of Stuttgart Germany

We present a motion planner for planning through space-time with dynamic obstacles, velocity constraints, and unknown arrival time. Our algorithm, Space-Time RRT* (ST-RRT*), is a probabilistically complete, bidirectional motion planning algorithm, which is asymptotically optimal with respect to the shortest arrival time. We experimentally evaluate ST-RRT* in both abstract (2D disk, 8D disk in cluttered spaces, and on a narrow passage problem), and simulated robotic path planning problems (sequential planning of 8DoF mobile robots, and 7DoF robotic arms). The proposed planner outperforms RRT-Connect and RRT* on both initial solution time, and attained final solution cost. The code for ST-RRT* is available in the Open Motion Planning Library (OMPL). Copyright © 2022, The Authors. 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

Deep Visual Heuristics: learning Feasibility of Mixed-Integer Programs for Manipulation Planning

Deep Visual Heuristics: Learning Feasibility of Mixed-Intege...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Danny Driess Ozgur Oguz Jung-Su Ha Marc Toussaint Machine Learning and Robotics Lab University of Stuttgart Germany Max Planck Institute for Intelligent Systems Stuttgart Germany

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

In this paper, we propose a deep neural network that predicts the feasibility of a mixed-integer program from visual input for robot manipulation planning. Integrating learning into task and motion planning is challenging, since it is unclear how the scene and goals can be encoded as input to the learning algorithm in a way that enables to generalize over a variety of tasks in environments with changing numbers of objects and goals. To achieve this, we propose to encode the scene and the target object directly in the image *** experiments show that our proposed network generalizes to scenes with multiple objects, although during training only two objects are present at the same time. By using the learned network as a heuristic to guide the search over the discrete variables of the mixed-integer program, the number of optimization problems that have to be solved to find a feasible solution or to detect infeasibility can greatly be reduced.

关键词： Planning Task analysis Robot sensing systems Neural networks Grasping Search problems

来源：评论

学校读者我要写书评

暂无评论

Escaping local optima in POMDP planning as inference

Escaping local optima in POMDP planning as inference

引用

10th International Conference on Autonomous Agents and Multiagent Systems 2011, AAMAS 2011

作者： Poupart, Pascal Lang, Tobias Toussaint, Marc David R. Cheriton School of Computer Science University of Waterloo ON Canada Machine Learning and Robotics Lab. FU Berlin Germany

来源：评论

学校读者我要写书评

暂无评论

Mechanisms of Social learning in Evolved Artificial Life

Mechanisms of Social Learning in Evolved Artificial Life

引用

2020 Conference on Artificial Life, ALIFE 2020

作者： Bartoli, Alberto Catto, Marco De Lorenzo, Andrea Medvet, Eric Talamini, Jacopo Machine Learning Lab. Department of Engineering and Architecture University of Trieste Italy Evolutionary Robotics and Artificial Life Lab. Department of Engineering and Architecture University of Trieste Italy

Adaptation of agents in artificial life scenarios is especially effective when agents may evolve, i.e., inherit traits from their parents, and learn by interacting with the environment. The learning process may be boosted with forms of social learning, i.e., by allowing an agent to learn by combining its experiences with knowledge transferred among agents. In this work, we tackle two specific questions regarding social learning and evolution: (a) from whom learners should learn? (b) how should knowledge be transferred? We address these questions by experimentally investigating two scenarios: a simple one in which the mechanism for evolution and learning is easily interpretable;a more complex and realistic artificial life scenario in which agents compete for survival. Experimental results show that social learning is more profitable when (a) the learners learn from a small set of good teachers and (b) the knowledge to be transferred is determined by teachers experience, rather than learner experience. © 2020 Massachusetts Institute of Technology.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Communication in Decision Making: Competition favors Inequality

Communication in Decision Making: Competition favors Inequal...

引用

2020 Conference on Artificial Life, ALIFE 2020

作者： Talamini, Jacopo Medvet, Eric Bartoli, Alberto De Lorenzo, Andrea Machine Learning Lab. Department of Engineering and Architecture University of Trieste Italy Evolutionary Robotics and Artificial Life Lab. Department of Engineering and Architecture University of Trieste Italy

We consider a multi-agent system in which the individual goal is to collect resources, but where the amount of collected resources depends also on others decision. Agents can communicate and can take advantage of being communicated other agents’ plan: therefore they may develop more profitable strategies. We wonder if some kind of collective behaviour, with respect to communication, emerges in this system without being explicitly promoted. To investigate this aspect, we design three different scenarios, respectively a cooperative, a competitive, and a mixed one, in which agents’ behaviors are individually learned by means of reinforcement learning. We consider different strategies concerning communication and learning, including no-communication, always-communication, and optional-communication. Experimental results show that always-communication leads to a collective behaviour with the best results in terms of both overall earned resources and equality between agents. On the other hand optional-communication strategy leads to similar collective strategies in some of these scenarios, but in other scenarios some agents develop individual behaviours that oppose to the collective welfare and thus result in high inequality. © 2020 Massachusetts Institute of Technology.

关键词：

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：