检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Doerr, Andreas Volpp, Michael Toussaint, Marc Trimpe, Sebastian Daniel, Christian Bosch Center for Artificial Intelligence Renningen Germany Max Planck Institute for Intelligent Systems Stuttgart/Tubingen Germany Machine Learning and Robotics Lab University of Stuttgart Germany

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently get stuck in local optima. This work addresses these weaknesses by combining recent improvements in the reuse of off-policy data and exploration in parameter space with deterministic behavioral policies. The resulting objective is amenable to standard neural network optimization strategies like stochastic gradient descent or stochastic gradient Hamiltonian Monte Carlo. Incorporation of previous rollouts via importance sampling greatly improves data-efficiency, whilst stochastic optimization schemes facilitate the escape from local optima. We evaluate the proposed approach on a series of continuous control benchmark tasks. The results show that the proposed algorithm is able to successfully and reliably learn solutions using fewer system interactions than standard policy gradient methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Control-Tree Optimization: an approach to MPC under discrete Partial Observability

arXiv

引用

arXiv 2023年

作者： Phiquepal, Camille Toussaint, Marc Machine Learning & Robotic Lab University of Stuttgart Germany Learning and Intelligent Systems Lab TU Berlin Germany

This paper presents a new approach to Model Predictive Control for environments where essential, discrete variables are partially observed. Under this assumption, the belief state is a probability distribution over a finite number of states. We optimize a control-tree where each branch assumes a given state-hypothesis. The control-tree optimization uses the probabilistic belief state information. This leads to policies more optimized with respect to likely states than unlikely ones, while still guaranteeing robust constraint satisfaction at all times. We apply the method to both linear and non-linear MPC with constraints. The optimization of the control-tree is decomposed into optimization subproblems that are solved in parallel leading to good scalability for high number of state-hypotheses. We demonstrate the real-time feasibility of the algorithm on two examples and show the benefits compared to a classical MPC scheme optimizing w.r.t. one single hypothesis. Copyright © 2023, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Path-Tree Optimization in Discrete Partially Observable Environments using Rapidly-Exploring Belief-Space Graphs

arXiv

引用

arXiv 2022年

作者： Phiquepal, Camille Orthey, Andreas Viennot, Nicolas Toussaint, Marc Machine Learning & Robotic Lab University of Stuttgart Germany Learning and Intelligent Systems Lab TU Berlin Germany

Robots often need to solve path planning problems where essential and discrete aspects of the environment are partially observable. This introduces a multi-modality, where the robot must be able to observe and infer the state of its environment. To tackle this problem, we introduce the Path-Tree Optimization (PTO) algorithm which plans a path-tree in belief-space. A path-tree is a tree-like motion with branching points where the robot receives an observation leading to a belief-state update. The robot takes different branches depending on the observation received. The algorithm assumes a deterministic observation model and is composed of three main steps. First, a rapidly-exploring random graph (RRG) on the state space is grown. Second, the RRG is expanded to a belief-space graph by querying the observation model. In a third step, dynamic programming is performed on the belief-space graph to extract a path-tree. The resulting path-tree combines exploration with exploitation i.e. it balances the need for gaining knowledge about the environment with the need for reaching the goal. We demonstrate the algorithm capabilities on navigation and mobile manipulation tasks, and show its advantage over a baseline using a task and motion planning approach (TAMP) both in terms of optimality and runtime. 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

Control-Tree Optimization: an approach to MPC under discrete Partial Observability

Control-Tree Optimization: an approach to MPC under discrete...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Camille Phiquepal Marc Toussaint Machine Learning & Robotic Lab University of Stuttgart Germany Learning and Intelligent Systems Lab TU Berlin Germany

关键词： Automation Scalability Conferences Probabilistic logic Real-time systems Probability distribution Observability

来源：评论

学校读者我要写书评

暂无评论

Understanding the geometry of workspace obstacles in Motion Optimization

Understanding the geometry of workspace obstacles in Motion ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Nathan Ratliff Marc Toussaint Stefan Schaal Autonomous Motion Department Max Planck Institute for Intelligent Systems Tübingen Germany Machine Learning and Robotics Lab University of Stuttgart Germany

ISBN: (纸本)9781479969241

What is it that makes movement around obstacles hard? The answer seems clear: obstacles contort the geometry of the workspace and make it difficult to leverage what we consider easy and intuitive straight-line Cartesian geometry. But is Cartesian motion actually easy? It's certainly well-understood and has numerous applications. But beneath the details of linear algebra and pseudoinverses, lies a non-trivial Riemannian metric driving the solution. Cartesian motion is easy only because the pseudoinverse, our powerhouse tool, correctly represents how Euclidean workspace geometry pulls back into the configuration space. In light of that observation, it reasons that motion through a field of obstacles could be just as easy as long as we correctly account for how those obstacles warp the geometry of the space. This paper explores extending our geometric model of the robot beyond the notion of a Cartesian workspace space to fully model and leverage how geometry changes in the presence of obstacles. Intuitively, impenetrable obstacles form topological holes and geodesics curve around them accordingly. We formalize this intuition and develop a general motion optimization framework called Riemannian Motion Optimization (RieMO) to efficiently find motions using our geometric models. Our experiments demonstrate that, for many problems, obstacle avoidance can be much more natural when placed within the right geometric context.

关键词： Geometry Optimization Measurement Approximation methods Trajectory Robots Kinematics

来源：评论

学校读者我要写书评

暂无评论

Optimizing motion primitives to make symbolic models more predictive

Optimizing motion primitives to make symbolic models more pr...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Andreas Orthey Marc Toussaint Nikolay Jetchev LAAS Université de Toulouse UPS INSA INP ISAE Centre National de la Recherche Scientifique Toulouse France Machine Learning and Robotics Laboratory University of Stuttgart Stuttgart Germany Machine Learning and Robotics Laboratory FU Berlin Berlin Germany

ISBN: (纸本)9781467356404

Solving complex robot manipulation tasks requires to combine motion generation on the geometric level with planning on a symbolic level. On both levels robotics research has developed a variety of mature methodologies, including geometric motion planning and motion primitive learning on the motor level as well as logic reasoning and relational Reinforcement learning methods on the symbolic level. However, their robust integration remains a great challenge. In this paper we approach one aspect of this integration by optimizing the motion primitives on the geometric level to be as consistent as possible with their symbolic predictions. The so optimized motion primitives increase the probability of a “successful” motion-meaning that the symbolic prediction was indeed achieved. Conversely, using these optimized motion primitives to collect new data about the effects of actions the learnt symbolic rules becomes more predictive and deterministic.

关键词： Trajectory Noise Robots Grasping Cost function Linear programming

来源：评论

学校读者我要写书评

暂无评论

Natural Gradient Shared Control

Natural Gradient Shared Control

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Yoojin Oh Shao-Wen Wu Marc Toussaint Jim Mainprice Machine Learning and Robotics Lab University of Stuttgart Germany Learning and Intelligent Systems Lab TU Berlin Berlin Germany Max Planck Institute for Intelligent Systems IS-MPI Tübingen Germany

ISBN: (数字)9781728160757

ISBN: (纸本)9781728160764

We propose a formalism for shared control, which is the problem of defining a policy that blends user control and autonomous control. The challenge posed by the shared autonomy system is to maintain user control authority while allowing the robot to support the user. This can be done by enforcing constraints or acting optimally when the intent is clear. Our proposed solution relies on natural gradients emerging from the divergence constraint between the robot and the shared policy. We approximate the Fisher information by sampling a learned robot policy and computing the local gradient to augment the user control when necessary. A user study performed on a manipulation task demonstrates that our approach allows for more efficient task completion while keeping control authority against a number of baseline methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Augmenting Human Policies using Riemannian Metrics for Human-Robot Shared Control

Augmenting Human Policies using Riemannian Metrics for Human...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Yoojin Oh Jean-Claude Passy Jim Mainprice Machine Learning and Robotics Lab University of Stuttgart Germany Max Planck Institute for Intelligent Systems Stuttgart Germany Max Planck Institute for Intelligent Systems Tübingen Germany

We present a shared control framework for teleoperation that combines the human and autonomous robot agents operating in different dimension spaces. The shared control problem is an optimization problem to maximize the human’s internal action-value function while guaranteeing that the shared control policy is close to the autonomous robot policy. This results in a state update rule that augments the human controls using the Riemannian metric that emerges from computing the curvature of the robot’s value function to account for any cost terms or constraints that the human operator may neglect when operating a redundant manipulator. In our experiments, we apply Linear Quadratic Regulators to locally approximate the robot policy using a single optimized robot trajectory, thereby preventing the need for an optimization step at each time step to determine the optimal policy. We show preliminary results of reach-and-grasp teleoperation tasks with a simulated human policy and a pilot user study using the VR headset and controllers. However, the mixed user preference ratings and quantitative results show that more investigation is required to prove the efficacy of the proposed paradigm.

关键词：

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 11

Escaping local optima in POMDP planning as inference

引用

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3

作者： Pascal Poupart Tobias Lang Marc Toussaint University of Waterloo Ontario Canada Machine Learning and Robotics Lab FU Berlin Germany

ISBN: (纸本)9780982657171

Planning as inference recently emerged as a versatile approach to decision-theoretic planning and reinforcement learning for single and multi-agent systems in fully and partially observable domains with discrete and continuous variables. Since planning as inference essentially tackles a non-convex optimization problem when the states are partially observable, there is a need to develop techniques that can robustly escape local optima. We propose two algorithms: the first one adds nodes to the controller according to an increasingly deep forward search, while the second one splits nodes in a greedy fashion to improve reward likelihood.

关键词： POMDPs EM planning

来源：评论

学校读者我要写书评

暂无评论

Natural gradient shared control

arXiv

引用

arXiv 2020年

作者： Oh, Yoojin Wu, Shao-Wen Toussaint, Marc Mainprice, Jim Machine Learning and Robotics Lab University of Stuttgart Germany Learning and Intelligent Systems Lab TU Berlin Berlin Germany Max Planck Institute for Intelligent Systems IS-MPI Tübingen Germany

关键词： Fisher information matrix

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：