检索结果-内蒙古大学图书馆

33rd International Conference on Automated Planning and Scheduling, ICAPS 2023

作者： Köckemann, Uwe Calisi, Daniele Gemignani, Guglielmo Renoux, Jennifer Saffiotti, Alessandro Center for Applied Autonomous Sensor Systems Örebro University Sweden Magazino GmbH Munich Germany

ISBN: (纸本)1577358813

Behavior Trees (BTs) are a formalism increasingly used to control the execution of robotic systems. The strength of BTs resides in their compact, hierarchical and transparent representation. However, when used in practical applications transparency is often hindered by the introduction of implicit runtime relations between nodes, e.g., because of data dependencies or hardware-related ordering constraints. Manually verifying the correctness of a BT with respect to these hidden relations is a tedious and error-prone task. This paper presents a modular planning-based approach for automatically testing BTs offline at design time, to identify possible executions that may violate given data and ordering constraints and to exhibit traces of these executions to help debugging. Our approach supports both basic and advanced BT node types, e.g., supporting parallel behaviors, and can be extended with other node types as needed. We evaluate our approach on BTs used in a commercially deployed robotics system and on a large set of randomly generated trees showing that our approach scales to realistic sizes of more than 3000 nodes. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Tracking Branched Deformable Linear Objects Using Particle Filtering on Depth Images

Tracking Branched Deformable Linear Objects Using Particle F...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Yuxuan Yang Johannes A. Stork Todor Stoyanov Center for Applied Autonomous Sensor Systems (AASS) Örebro University Sweden

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Branched deformable linear objects (BDLOs), such as wire harnesses, are important connecting components in manufacturing industries. However, due to deformability, a lack of distinct visual features, and complex branched structure, automating tasks involving these BDLOs remains a challenge. In this paper, we propose a particle-filter-based method to track the state of a BDLO. To circumvent the high cost of tracking the complex high-dimensional BDLO state, we instead track each branch as an individual B-spline. Our method learns a data-driven model to predict the likelihood of each particle conditioned on depth image observation. In contrast to current state-of-the-art approaches based on non-rigid registration, we do not require pre-segmenting the BDLO, thus alleviating a strong and limiting assumption. We train our approach on domain-randomized depth data from simulation and achieve zero-shot transfer to real-world BDLOs, achieving state-of-the- art tracking performance when the pre-segmentation fails.

关键词： Manufacturing industries Visualization Limiting Costs Computer aided software engineering Automation Filtering Predictive models Wire Splines (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Visual Noun Modifiers: The Problem of Binding Visual and Linguistic Cues*

Visual Noun Modifiers: The Problem of Binding Visual and Lin...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Mohamadreza Faridghasemnia Jennifer Renoux Alessandro Saffiotti Center for Applied Autonomous Sensor Systems (AASS) Örebro University Sweden

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In many robotic applications, especially those involving humans and the environment, linguistic and visual information must be processed jointly and bound together. Existing works either encode the image or the language into a subsymbolic space, like the CLIP model, or create a symbolic space of extracted information, like the object detection models. In this paper, we propose to describe images by nouns and modifiers and introduce a new embedded binding space where the linguistic and visual cues can effectively be bound. We investigate how state-of-the-art models perform in recognizing nouns and modifiers from images, and propose our method by introducing a dataset and CLIP-like recognition techniques based on transfer learning and metric learning. We show real-world experiments that demonstrate the practical applicability of our approach to robotics applications. Our results indicate that our method can surpass the state-of-the-art in recognizing nouns and modifiers from images. Interestingly, our method exhibits a language characteristic related to context sensitivity.

关键词： Visualization Image recognition Sensitivity Transfer learning Object detection Linguistics Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Learning Extrinsic Dexterity with Parameterized Manipulation Primitives

Learning Extrinsic Dexterity with Parameterized Manipulation...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Shih-Min Yang Martin Magnusson Johannes A. Stork Todor Stoyanov Center for Applied Autonomous Sensor Systems (AASS) Örebro University Sweden

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Many practically relevant robot grasping problems feature a target object for which all grasps are occluded, e.g., by the environment. Single-shot grasp planning invariably fails in such scenarios. Instead, it is necessary to first manipulate the object into a configuration that affords a grasp. We solve this problem by learning a sequence of actions that utilize the environment to change the object’s pose. Concretely, we employ hierarchical reinforcement learning to combine a sequence of learned parameterized manipulation primitives. By learning the low-level manipulation policies, our approach can control the object’s state through exploiting interactions between the object, the gripper, and the environment. Designing such a complex behavior analytically would be infeasible under uncontrolled conditions, as an analytic approach requires accurate physical modeling of the interaction and contact dynamics. In contrast, we learn a hierarchical policy model that operates directly on depth perception data, without the need for object detection, pose estimation, or manual design of controllers. We evaluate our approach on picking box-shaped objects of various weight, shape, and friction properties from a constrained table-top workspace. Our method transfers to a real robot and is able to successfully complete the object picking task in 98% of experimental trials.

关键词： Training Shape Pose estimation Grasping Reinforcement learning Object detection Planning

来源：评论

学校读者我要写书评

暂无评论

DataSP: a differential all-to-all shortest path algorithm for learning costs and predicting paths with context 24

DataSP: a differential all-to-all shortest path algorithm fo...

引用

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Alan A. Lahoud Erik Schaffernicht Johannes A. Stork Center for Applied Autonomous Sensor Systems (AASS) Örebro University Örebro Sweden

Learning latent costs of transitions on graphs from trajectories demonstrations under various contextual features is challenging but useful for path planning. Yet, existing methods either oversimplify cost assumptions or scale poorly with the number of observed trajectories. This paper introduces DataSP, a differentiable all-to-all shortest path algorithm to facilitate learning latent costs from trajectories. It allows to learn from a large number of trajectories in each learning step without additional computation. Complex latent cost functions from contextual features can be represented in the algorithm through a neural network approximation. We further propose a method to sample paths from DataSP in order to mimic observed paths' distributions. We prove that the inferred distribution follows the maximum entropy principle. We show that DataSP outperforms state-of-the-art differentiable combinatorial solver and classical machine learning approaches in predicting paths on graphs. The code is available at https://***/AlanLahoud/dataSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Should I Lead or Follow? Understanding Initiative Levels in Human-AI Collaborative Gameplay

When Should I Lead or Follow? Understanding Initiative Level...

引用

2024 ACM Designing Interactive systems Conference, DIS 2024

作者： Lobo, Inês Koch, Janin Renoux, Jennifer Batina, Inês Prada, Rui INESC-ID and Instituto Superior Técnico Universidade de Lisboa Portugal ExSitu Université Paris-Saclay CNRS Inria France Center for Applied Autonomous Sensor Systems Örebro University Sweden

ISBN: (纸本)9798400705830

Dynamics in Human-AI interaction should lead to more satisfying and engaging collaboration. Key open questions are how to design such interactions and the role personal goals and expectations play. We developed three AI partners of varying initiative (leader, follower, shifting) in a collaborative game called Geometry Friends. We conducted a within-subjects experiment with 60 participants to assess personal AI partner preference and performance satisfaction as well as perceived warmth and competence of AI partners. Results show that AI partners following human initiative are perceived as warmer and more collaborative. However, some participants preferred AI leaders for their independence and speed, despite being seen as less friendly. This suggests that assigning a leadership role to the AI partner may be suitable for time-sensitive scenarios. We identify design factors for developing collaborative AI agents with varying levels of initiative to create more efective human-AI teams that consider context and individual preference. © 2024 Copyright held by the owner/author(s).

关键词： Collaboration Preference Collaborative Game Human-AI Collaboration Initiative in AI Partners

来源：评论

学校读者我要写书评

暂无评论

Learn from Robot: Transferring Skills for Diverse Manipulation via Cycle Generative Networks

Learn from Robot: Transferring Skills for Diverse Manipulati...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Quantao Yang Johannes A. Stork Todor Stoyanov Center for Applied Autonomous Sensor Systems (AASS) Örebro University Sweden

Reinforcement learning (RL) has shown impressive results on a variety of robot tasks, but it requires a large amount of data for learning a single RL policy. However, in manufacturing there is a wide demand of reusing skills from different robots and it is hard to transfer the learned policy to different hardware due to diverse robot body morphology, kinematics, and dynamics. In this paper, we address the problem of transferring policies between different robot platforms. We learn a set of skills on each specific robot and represent them in a latent space. We propose to transfer the skills between different robots by mapping latent action spaces through a cycle generative network in a supervised learning manner. We extend the policy model learned on one robot with a pre-trained generative network to enable the robot to learn from the skill of another robot. We evaluate our method on several simulated experiments and demonstrate that our Learn from Robot (LfR) method accelerates new skill learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Likely, Light, and Accurate Context-Free Clusters-based Trajectory Prediction

Likely, Light, and Accurate Context-Free Clusters-based Traj...

引用

International Conference on Intelligent Transportation

作者： Tiago Rodrigues de Almeida Oscar Martinez Mozos Center for Applied Autonomous Sensor Systems (AASS) Örebro University Örebro Sweden

autonomous systems in the road transportation network require intelligent mechanisms that cope with uncertainty to foresee the future. In this paper, we propose a multi-stage probabilistic approach for trajectory forecasting: trajectory transformation to displacement space, clustering of displacement time series, trajectory proposals, and ranking proposals. We introduce a new deep feature clustering method, underlying self-conditioned GAN, which copes better with distribution shifts than traditional methods. Additionally, we propose novel distance-based ranking proposals to assign probabilities to the generated trajectories that are more efficient yet accurate than an auxiliary neural network. The overall system surpasses context-free deep generative models in human and road agents trajectory data while performing similarly to point estimators when comparing the most probable trajectory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diversity for Contingency: Learning Diverse Behaviors for Efficient Adaptation and Transfer

arXiv

引用

arXiv 2023年

作者： Rietz, Finn Stork, Johannes Andreas Adaptive and Interpretable Learning Systems Lab Center for Applied Autonomous Sensor Systems Örebro University Sweden

Discovering all useful solutions for a given task is crucial for transferable RL agents, to account for changes in the task or transition dynamics. This is not considered by classical RL algorithms that are only concerned with finding the optimal policy, given the current task and dynamics. We propose a simple method for discovering all possible solutions of a given task, to obtain an agent that performs well in the transfer setting and adapts quickly to changes in the task or transition dynamics. Our method iteratively learns a set of policies, while each subsequent policy is constrained to yield a solution that is unlikely under all previous policies. Unlike prior methods, our approach does not require learning additional models for novelty detection and avoids balancing task and novelty reward signals, by directly incorporating the constraint into the action selection and optimization steps. © 2023, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Experimental validation of domain knowledge assisted robotic exploration and source localization

Experimental validation of domain knowledge assisted robotic...

引用

2021 IEEE International Conference on autonomous systems, ICAS 2021

作者： Wiedemann, Thomas Shutin, Dmitriy Lilienthal, Achim J. Institute of Communications and Navigation German Aerospace Center Oberpfaffenhofen Germany Örebro University Center of Applied Autonomous Sensor Systems Örebro Sweden

ISBN: (纸本)9781728172897

In situations where toxic or dangerous airborne material is leaking, mobile robots equipped with gas sensors are a safe alternative to human reconnaissance. This work presents the Domain Knowledge Assisted Robotic Exploration and Source Localization (DARES) approach. It allows a multi-robot system to localize multiple sources or leaks autonomously and independently of a human operator. The probabilistic approach builds upon domain knowledge in the form of a physical model of gas dispersion and the a priori assumption that the dispersion process is driven by multiple but sparsely distributed sources. A formal criterion is used to guide the robots to informative measurement locations and enables inference of the source distribution based on gas concentration measurements. Small-scale indoor experiments under controlled conditions are presented to validate the approach. In all three experiments, three rovers successfully localized two ethanol sources. © 2021 IEEE.

关键词： Mobile robots

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：