检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Maene, Jaron Derkinderen, Vincent De Raedt, Luc KU Leuven Department of Computer Science Leuven Belgium Örebro University Centre for Applied Autonomous Sensor Systems Örebro Sweden

The limitations of purely neural learning have sparked an interest in probabilistic neurosymbolic models, which combine neural networks with probabilistic logical reasoning. As these neurosymbolic models are trained with gradient descent, we study the complexity of differentiating probabilistic reasoning. We prove that although approximating these gradients is intractable in general, it becomes tractable during training. Furthermore, we introduce WeightME, an unbiased gradient estimator based on model sampling. Under mild assumptions, WeightME approximates the gradient with probabilistic guarantees using a logarithmic number of calls to a SAT solver. Lastly, we evaluate the necessity of these guarantees on the gradient. Our experiments indicate that the existing biased approximations indeed struggle to optimize even when exact solving is still feasible. Copyright 2024 by the author(s)

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

autonomous Navigation of Wheel Loaders using Task Decomposition and Reinforcement Learning 19

Autonomous Navigation of Wheel Loaders using Task Decomposit...

引用

19th IEEE International Conference on Automation Science and Engineering, CASE 2023

作者： Borngrund, Carl Bodin, Ulf Sandin, Fredrik Andreasson, Henrik Luleå University of Technology Eislab Luleå97187 Sweden Örebro University Centre for Applied Autonomous Sensor Systems 70182 Sweden

ISBN: (纸本)9798350320695

The short-loading cycle is a repetitive task performed in high quantities making it a good candidate for automation. Expert operators perform this task to upkeep high productivity while minimizing the environmental impact of using energy to propel the wheel loader. The need to balance productivity and environmental performance is essential for the sub-task of navigating the wheel loader between the pile of material and a dump truck receiving the material. This task is further complicated by behaviours of the wheel loader such as wheel slip depending on the tire-to-surface friction that is hard to model. Such uncertainties motivate the use of data-driven and adaptable approaches like reinforcement learning to automate navigation. In this paper, we examine the possibility to use reinforcement learning for the navigation sub-task. We focus on the process of developing a solution to the complete sub-task by decomposing it into two distinct steps and training two different agents to perform them separately. These steps are reversing from the pile and approaching the dump truck. The agents are trained in a simulation environment in which the wheel loader is modelled. Our results indicate that task decomposition can be helpful in performing the navigation compared to training a single agent for the entire sub-task. We present unsuccessful experiments using a single agent for the entire sub-task to illustrate difficulties associated with such an approach. A video of the results is available online11Video available at https://***/IZbgvHvSltI. © 2023 IEEE.

关键词： Wheels

来源：评论

学校读者我要写书评

暂无评论

Learning the Approach During the Short-loading Cycle Using Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Borngrund, Carl Bodin, Ulf Andreasson, Henrik Sandin, Fredrik EISLAB Luleå University of Technology Luleå97187 Sweden The Centre for Applied Autonomous Sensor Systems Örebro University 70182 Sweden

The short-loading cycle is a repetitive task performed in high quantities, making it a great alternative for automation. In the short-loading cycle, an expert operator navigates towards a pile, fills the bucket with material, navigates to a dump truck, and dumps the material into the tipping body. The operator has to balance the productivity goal while minimising the fuel usage, to maximise the overall efficiency of the cycle. In addition, difficult interactions, such as the tyre-to-surface interaction further complicate the cycle. These types of hard-to-model interactions that can be difficult to address with rule-based systems, together with the efficiency requirements, motivate us to examine the potential of data-driven approaches. In this paper, the possibility of teaching an agent through reinforcement learning to approach a dump truck's tipping body and get in position to dump material in the tipping body is examined. The agent is trained in a 3D simulated environment to perform a simplified navigation task. The trained agent is directly transferred to a real vehicle, to perform the same task, with no additional training. The results indicate that the agent can successfully learn to navigate towards the dump truck with a limited amount of control signals in simulation and when transferred to a real vehicle, exhibits the correct behaviour. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

KLAY: ACCELERATING ARITHMETIC CIRCUITS FOR NEUROSYMBOLIC AI

arXiv

引用

arXiv 2024年

作者： Maene, Jaron Derkinderen, Vincent Martires, Pedro Zuidberg Dos Department of Computer Science KU Leuven Leuven Belgium Centre for Applied Autonomous Sensor Systems Örebro University Örebro Sweden

A popular approach to neurosymbolic AI involves mapping logic formulas to arithmetic circuits (computation graphs consisting of sums and products) and passing the outputs of a neural network through these circuits. This approach enforces symbolic constraints onto a neural network in a principled and end-to-end differentiable way. Unfortunately, arithmetic circuits are challenging to run on modern tensor accelerators as they exhibit a high degree of irregular sparsity. To address this limitation, we introduce knowledge layers (KLAY), a new data structure to represent arithmetic circuits that can be efficiently parallelized on GPUs. Moreover, we contribute two algorithms used in the translation of traditional circuit representations to KLAY and a further algorithm that exploits parallelization opportunities during circuit evaluations. We empirically show that KLAY achieves speedups of multiple orders of magnitude over the state of the art, thereby paving the way towards scaling neurosymbolic AI to larger real-world applications. © 2024, CC BY.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

autonomous Navigation of Wheel Loaders using Task Decomposition and Reinforcement Learning

Autonomous Navigation of Wheel Loaders using Task Decomposit...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Carl Borngrund Ulf Bodin Fredrik Sandin Henrik Andreasson EISLAB Luleå University of Technology Luleå Sweden Centre for Applied Autonomous Sensor Systems Örebro University Sweden

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revisiting Distribution-Based Registration Methods

Revisiting Distribution-Based Registration Methods

引用

European Conference on Mobile Robots (ECMR)

作者： Himanshu Gupta Henrik Andreasson Martin Magnusson Simon Julier Achim J. Lilientha Centre for Applied Autonomous Sensor Systems (AASS) Orebro University Sweden Department of Computer Science University College London UK Perception for Intelligent Systems Technical University of Munich Germany and Centre for Applied Autonomous Sensor Systems (AASS) Orebro University Sweden

Normal Distribution Transformation (NDT) registration is a fast, learning-free point cloud registration algorithm that works well in diverse environments. It uses the compact NDT representation to represent point clouds or maps as a spatial probability function that models the occupancy likelihood in an environment. However, because of the grid discretization in NDT maps, the global minima of the registration cost function do not always correlate to ground truth, particularly for rotational alignment. In this study, we examined the NDT registration cost function in-depth. We evaluated three modifications (Student-t likelihood function, inflated covariance/heavily broadened likelihood curve, and overlapping grid cells) that aim to reduce the negative impact of discretization in classical NDT registration. The first NDT modification improves likelihood estimates for matching the distributions of small population sizes; the second modification reduces discretization artifacts by broadening the likelihood tails through covariance inflation; and the third modification achieves continuity by creating the NDT representations with overlapping grid cells (without increasing the total number of cells). We used the Pomerleau Dataset evaluation protocol for our experiments and found significant improvements compared to the classic NDT D2D registration approach (27.7% success rate) using the registration cost functions “heavily broadened likelihood NDT” (HBL- NDT) (34.7% success rate) and “over-lapping grid cells NDT” (OGC-NDT) (33.5% success rate). However, we could not observe a consistent improvement using the Student-t likelihood-based registration cost function (22.2% success rate) over the NDT P2D registration cost function (23.7% success rate). A comparative analysis with other state-of-art registration algorithms is also presented in this work. We found that HBL-NDT worked best for easy initial pose difficulties scenarios making it suitable for consecutive point cloud re

关键词：

来源：评论

学校读者我要写书评

暂无评论

Housekeeping Using Multi-Agent Service Robotics

Housekeeping Using Multi-Agent Service Robotics

引用

International Conference on Robotics and Artificial Intelligence (ICRAI)

作者： Muhammad Faiq Malik Haris Shahid Muhammad Haris Saleem Hassan Nazir Ahmed Nouman Mechatronics Engineering Department University of Engineering & Technology Taxila Pakistan Centre for Applied Autonomous Sensor Systems (AASS) Örebro University Örebro Sweden

Service robotics in dynamic environments is a challenging yet exciting field that has witnessed incredible advances in the last few decades. The credit for these advancements goes to artificial intelligence and robotics technological progressions. The housekeeping domain is an example of a service robotics domain. A high-level task planner can compute a plan of action, while low-level functionalities like perception and motion planning can ensure feasibility. We propose a solution to the housekeeping problem that utilizes the expressiveness of action language C+ to formalize actions and compute an action plan. To check for feasibility in the real world, we execute the action plans in a physics simulator, GAZEBO. We also propose benchmark instances for the housekeeping domain and evaluate our planning and execution times approach. We report possible execution failures for the benchmark instances and offer plausible solutions, such as hybrid planning, plan execution monitoring, and conditional planning.

关键词： Industries Automation Service robots Computational modeling Benchmark testing Planning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Applications of Hybrid Conditional Planning in Service Robotics

Applications of Hybrid Conditional Planning in Service Robot...

引用

International Conference on Robotics and Artificial Intelligence (ICRAI)

作者： Ahmed Nouman Muhammad Khurram Saleem Centre for Applied Autonomous Sensor Systems (AASS) Örebro University Örebro Sweden Mechatronics Engineering Department University of Engineering & Technology Taxila Pakistan

Hybrid planning computes task plans in full observability (a sequence of possible actuation actions) via the integration of low-level feasibility checks in classical planning approaches. Conditional planning extends the classical planning framework to account for plans under partial observability. We use a hybrid conditional planning approach to compute plans that include sensing and actuation actions in solving real-world problems by addressing uncertainties due to incomplete information at the planning phase. We generate a hybrid conditional plan of actions using parallel instances of a non-monotonic hybrid HCPLAN that supports defaults, integration of external computations, and non-deterministic actions. We show our hybrid conditional planning framework's HCPLAN applicability through service robotics scenarios with manipulation and navigation tasks. Furthermore, we evaluate the effect of parallel threads on the computation of hybrid conditional framework on different benchmark scenarios for the service robotics domains.

关键词： Uncertainty Service robots Navigation Knowledge based systems Robot sensing systems Hybrid power systems Planning

来源：评论

学校读者我要写书评

暂无评论

On the hardness of probabilistic neurosymbolic learning 24

On the hardness of probabilistic neurosymbolic learning

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jaron Maene Vincent Derkinderen Luc De Raedt KU Leuven Department of Computer Science Leuven Belgium KU Leuven Department of Computer Science Leuven Belgium and Örebro University Centre for Applied Autonomous Sensor Systems Örebro Sweden

关键词：

来源：评论

学校读者我要写书评

暂无评论

Declarative Probabilistic Logic Programming in Discrete-Continuous Domains

arXiv

引用

arXiv 2023年

作者： Dos Martires, Pedro Zuidberg De Raedt, Luc Kimmig, Angelika Centre for Applied Autonomous Sensor Systems Örebro University Sweden Department of Computer Science KU Leuven Belgium Leuven.AI Belgium

Over the past three decades, the logic programming paradigm has been successfully expanded to support probabilistic modeling, inference and learning. The resulting paradigm of probabilistic logic programming (PLP) and its programming languages owes much of its success to a declarative semantics, the so-called distribution semantics. However, the distribution semantics is limited to discrete random variables only. While PLP has been extended in various ways for supporting hybrid, that is, mixed discrete and continuous random variables, we are still lacking a declarative semantics for hybrid PLP that not only generalizes the distribution semantics and the modeling language but also the standard inference algorithm that is based on knowledge compilation. We contribute the measure semantics together with the hybrid PLP language DC-ProbLog (where DC stands for distributional clauses) and its inference engine infinitesimal algebraic likelihood weighting (IALW). These have the original distribution semantics, standard PLP languages such as ProbLog, and standard inference engines for PLP based on knowledge compilation as special cases. Thus, we generalize the state of the art of PLP towards hybrid PLP in three different aspects: semantics, language and inference. Furthermore, IALW is the first inference algorithm for hybrid probabilistic programming based on knowledge compilation. © 2023, CC BY.

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：