检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

A Probabilistic Framework for Constrained Manipulations and ...

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

Automated Planning Domain Inference for Task and Motion Planning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Jinbang Tao, Allen Marco, Rozilyn Bogdanovic, Miroslav Kelly, Jonathan Shkurti, Florian Space and Terrestrial Autonomous Systems Lab Canada Robot Vision and Learning Lab University of Toronto Robotics Institute Canada

Task and motion planning (TAMP) frameworks address long and complex planning problems by integrating high-level task planners with low-level motion planners. However, existing TAMP methods rely heavily on the manual design of planning domains that specify the preconditions and postconditions of all high-level actions. This paper proposes a method to automate planning domain inference from a handful of test-time trajectory demonstrations, reducing the reliance on human design. Our approach incorporates a deep learning-based estimator that predicts the appropriate components of a domain for a new task and a search algorithm that refines this prediction, reducing the size and ensuring the utility of the inferred domain. Our method is able to generate new domains from minimal demonstrations at test time, enabling robots to handle complex tasks more efficiently. We demonstrate that our approach outperforms behavior cloning baselines, which directly imitate planner behavior, in terms of planning performance and generalization across a variety of tasks. Additionally, our method reduces computational costs and data amount requirements at test time for inferring new planning domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

Deep visual reasoning: learning to predict action sequences for task and motion planning from an initial scene image

学校读者我要写书评

暂无评论

arXiv 2020年

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

In this paper, we propose a deep convolutional recurrent neural network that predicts action sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete level (e.g. first-order logic) with continuous motion planning such as nonlinear trajectory optimization. Due to the great combinatorial complexity of possible discrete action sequences, a large number of optimization/motion planning problems have to be solved to find a solution, which limits the scalability of these approaches. To circumvent this combinatorial complexity, we develop a neural network which, based on an initial image of the scene, directly predicts promising discrete action sequences such that ideally only one motion planning problem has to be solved to find a solution to the overall TAMP problem. A key aspect is that our method generalizes to scenes with many and varying number of objects, although being trained on only two objects at a time. This is possible by encoding the objects of the scene in images as input to the neural network, instead of a fixed feature vector. Results show runtime improvements of several magnitudes. Video: https://***/i8yyEbbvoEk Copyright © 2020, The Authors. All rights reserved.

关键词： Motion planning

Plan-based relaxed reward shaping for goal-directed tasks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Schubert, Ingmar Oguz, Ozgur S. Toussaint, Marc Learning and Intelligent Systems Group TU Berlin Germany Max Planck Institute for Intelligent Systems Stuttgart Germany Machine Learning and Robotics Lab University of Stuttgart Germany

In high-dimensional state spaces, the usefulness of Reinforcement learning (RL) is limited by the problem of exploration. This issue has been addressed using potential-based reward shaping (PB-RS) previously. In the present work, we introduce Final-Volume-Preserving Reward Shaping (FV-RS). FV-RS relaxes the strict optimality guarantees of PB-RS to a guarantee of preserved long-term behavior. Being less restrictive, FV-RS allows for reward shaping functions that are even better suited for improving the sample efficiency of RL algorithms. In particular, we consider settings in which the agent has access to an approximate plan. Here, we use examples of simulated robotic manipulation tasks to demonstrate that plan-based FV-RS can indeed significantly improve the sample efficiency of RL over plan-based PB-RS. © 2021, CC BY.

关键词： Efficiency

Is Data All That Matters? the Role of Control Frequency for learning-Based Sampled-Data Control of Uncertain systems

学校读者我要写书评

暂无评论

Is Data All That Matters? the Role of Control Frequency for ...

American Control Conference (ACC)

作者： Ralf Römer Lukas Brunke Siqi Zhou Angela P. Schoellig Learning Systems and Robotics Lab (***) School of Computation Information and Technology and the Munich Institute for Robotics and Machine Intelligence (MIRMI) Technical University of Munich Germany

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

learning models or control policies from data has become a powerful tool to improve the performance of uncertain systems. While a strong focus has been placed on increasing the amount and quality of data to improve performance, data can never fully eliminate uncertainty, making feedback necessary to ensure stability and performance. We show that the control frequency at which the input is recalculated is a crucial design parameter, yet it has hardly been considered before. We address this gap by combining probabilistic model learning and sampled-data control. We use Gaussian processes (GPs) to learn a continuous-time model and compute a corresponding discrete-time controller. The result is an uncertain sampled-data control system, for which we derive robust stability conditions. We formulate semidefinite programs to compute the minimum control frequency required for stability and to optimize performance. As a result, our approach enables us to study the effect of both control frequency and data on stability and closed-loop performance. We show in numerical simulations of a quadrotor that performance can be improved by increasing either the amount of data or the control frequency, and that we can trade off one for the other. For example, by increasing the control frequency by 33%, we can reduce the number of data points by half while still achieving similar performance.

关键词： Uncertain systems Uncertainty Robust stability Computational modeling Control systems Stability analysis Data models

Natural Gradient Shared Control

学校读者我要写书评

暂无评论

Natural Gradient Shared Control

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：

Natural gradient shared control

学校读者我要写书评

暂无评论

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

Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement learning Agents

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bejarano, Federico Pizarro Brunke, Lukas Schoellig, Angela P. The Learning Systems and Robotics Lab University of Toronto Canada The University of Toronto Robotics Institute The Vector Institute for Artificial Intelligence Toronto Canada Germany

Reinforcement learning (RL) controllers are flexible and performant but rarely guarantee safety. Safety filters impart hard safety guarantees to RL controllers while maintaining flexibility. However, safety filters can cause undesired behaviours due to the separation between the controller and the safety filter, often degrading performance and robustness. In this paper, we analyze several modifications to incorporating the safety filter in training RL controllers rather than solely applying it during evaluation. The modifications allow the RL controller to learn to account for the safety filter, improving performance. This paper presents a comprehensive analysis of training RL with safety filters, featuring simulated and real-world experiments with a Crazyflie 2.0 drone. We examine how various training modifications and hyperparameters impact performance, sample efficiency, safety, and chattering. Our findings serve as a guide for practitioners and researchers focused on safety filters and safe RL. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning