检索结果-内蒙古大学图书馆

Anticipating Human Intention for Full-Body Motion Prediction in Object Grasping and Placing Tasks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kratzer, Philipp Midlagajni, Niteesh Balachandra Toussaint, Marc Mainprice, Jim Machine Learning and Robotics Lab University of Stuttgart Germany Humans to Robots Motions Research Group HRM University of Stuttgart Germany Learning and Intelligent Systems Lab Technical University of Berlin Germany

关键词： Motion estimation

Regression with comparisons: escaping the curse of dimensionality with ordinal information

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of machine learning Research 2020年第1期21卷 6480-6533页

作者： Yichong Xu Sivaraman Balakrishnan Aarti Singh Artur Dubrawski Machine Learning Department Department of Statistics and Data Science Machine Learning Department Auton Lab The Robotics Institute Carnegie Mellon University Pittsburgh PA

In supervised learning, we typically leverage a fully labeled dataset to design methods for function estimation or prediction. In many practical situations, we are able to obtain alternative feedback, possibly at a low cost. A broad goal is to understand the usefulness of, and to design algorithms to exploit, this alternative feedback. In this paper, we consider a semi-supervised regression setting, where we obtain additional ordinal (or comparison) information for the unlabeled samples. We consider ordinal feedback of varying qualities where we have either a perfect ordering of the samples, a noisy ordering of the samples or noisy pairwise comparisons between the samples. We provide a precise quantification of the usefulness of these types of ordinal feedback in both nonparametric and linear regression, showing that in many cases it is possible to accurately estimate an underlying function with a very small labeled set, effectively escaping the curse of dimensionality. We also present lower bounds, that establish fundamental limits for the task and show that our algorithms are optimal in a variety of settings. Finally, we present extensive experiments on new datasets that demonstrate the efficacy and practicality of our algorithms and investigate their robustness to various sources of noise and model misspecification.

关键词： pairwise comparison ranking regression interactive learning

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

Asymptotically Optimal Belief Space Planning in Discrete Partially-Observable Domains

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Freund, Janis Eric Phiquepal, Camille Orthey, Andreas Toussaint, Marc Technical University of Berlin Germany Realtime Robotics Inc. BostonMA United States Machine Learning & Robotics Lab University of Stuttgart Germany

Robots often have to operate in discrete partially observable worlds, where the states of world are only observable at runtime. To react to different world states, robots need contingencies. However, computing contingencies is costly and often non-optimal. To address this problem, we develop the improved path tree optimization (PTO) method. PTO computes motion contingencies by constructing a tree of motion paths in belief space. This is achieved by constructing a graph of configurations, then adding observation edges to extend the graph to belief space. Afterwards, we use a dynamic programming step to extract the path tree. PTO extends prior work by adding a camera-based state sampler to improve the search for observation points. We also add support to non-euclidean state spaces, provide an implementation in the open motion planning library (OMPL), and evaluate PTO on four realistic scenarios with a virtual camera in up to 10-dimensional state spaces. We compare PTO with a default and with the new camera-based state sampler. The results indicate that the camera-based state sampler improves success rates in 3 out of 4 scenarios while having a significant lower memory footprint. This makes PTO an important contribution to advance the state-of-the-art for discrete belief space planning. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamic programming

Entropy-based strategies for physical exploration of the environment's degrees of freedom

学校读者我要写书评

暂无评论

Entropy-based strategies for physical exploration of the env...

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Stefan Otte Johannes Kulick Marc Toussaint Oliver Brock Machine Learning and Robotics Lab Universität Stuttgart Germany Robotics and Biology Laboratory Technische Universität Berlin Germany

Physical exploration refers to the challenge of autonomously discovering and learning how to manipulate the environment's degrees of freedom (DOF)-by identifying promising points of interaction and pushing or pulling object parts to reveal DOF and their properties. Recent existing work focused on sub-problems like estimating DOF parameters from given data. Here, we address the integrated problem, focusing on the higher-level strategy to iteratively decide on the next exploration point before applying motion generation methods to execute the explorative action and data analysis methods to interpret the feedback. We propose to decide on exploration points based on the expected information gain, or change in entropy in the robot's current belief (uncertain knowledge) about the DOF. To this end, we first define how we represent such a belief. This requires dealing with the fact that the robot initially does not know which random variables (which DOF, and depending on their type, which DOF properties) actually exist. We then propose methods to estimate the expected information gain for an exploratory action. We analyze these strategies in simple environments and evaluate them in combination with full motion planning and data analysis in a physical simulation environment.

关键词： Joints Entropy Robots Random variables Trajectory Uncertainty Friction

Opening a lockbox through physical exploration

学校读者我要写书评

暂无评论

Opening a lockbox through physical exploration

IEEE-RAS International Conference on Humanoid Robots

作者： Manuel Baum Matthew Bernstein Roberto Martin-Martin Sebastian Höfer Johannes Kulick Marc Toussaint Alex Kacelnik Oliver Brock Robotics and Biology Lab (RBO) Technische Universität Berlin Machine Learning and Robotics Lab (MLR) Universität Stuttgart Department of Zoology Oxford University

ISBN: (纸本)9781538646793

How can we close the gap between animals and robots when it comes to intelligently interacting with the environment? On our quest for answers, we have investigated the problem of physically exploring complex mechanical puzzles, called lockboxes. Biologists have discovered that cockatoos are intrinsically motivated to explore and solve such problems through physical explorative behavior. In this work, we study how different strategies shape the robots' exploration, given basic perception-action skills. Our evaluation highlights the influence of different statistical priors on the performance of the exploration strategies, showing that not only a range of computational methods, but also a range of priors could explain different exploration behaviors. We carry out our study of exploration strategies both in simulation and on two robot platforms. This first step towards a fully integrated real-world system allowed us to identify and remove limitations of our prior theoretical work on cross-entropy-based exploration when applied to complex realistic scenarios. In this paper we propose novel variants of this strategy and our experiments verify that the cross-entropy method performs well on a physical lockbox analogue of the cockatoo apparatus, and can generalize to lockboxes of different properties.

关键词： Robot sensing systems Entropy Kinematics Robot kinematics Planning

Sparse Gaussian process regression for compliant, real-time robot control

学校读者我要写书评

暂无评论

Sparse Gaussian process regression for compliant, real-time ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Jens Schreiter Peter Englert Duy Nguyen-Tuong Marc Toussaint Robert Bosch GmbH Department for Cognitive Systems Stuttgart Germany University of Stuttgart Machine Learning and Robotics Laboratory Stuttgart Germany

ISBN: (纸本)9781479969241

Sparse Gaussian process (GP) models provide an efficient way to perform regression on large data sets. The key idea is to select a representative subset of the available training data, which induces the sparse GP model approximation. In the past, a variety of selection criteria for GP approximation have been proposed, but they either lack accuracy or suffer from high computational costs. In this paper, we introduce a novel and straightforward criterion for successive selection of training points used for GP model approximation. The proposed algorithm allows a fast and efficient selection of training points, while being competitive in learning performance. As evaluation, we employ our approach in learning inverse dynamics models for robot control using very large data sets (e.g. 500.000 samples). It is demonstrated in experiments that our approximated GP model is sufficiently fast for real-time prediction in robot control. Comparisons with other state-of-the-art approximation techniques show that our proposed approach is significantly faster, while being competitive to generalization accuracy.

关键词： Approximation methods Training Ground penetrating radar Computational modeling Data models Robots Accuracy

learning Efficient Constraint Graph Sampling for Robotic Sequential Manipulation

学校读者我要写书评

暂无评论

Learning Efficient Constraint Graph Sampling for Robotic Seq...

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