检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Char, Ian Mehta, Viraj Villaflor, Adam Dolan, John M. Schneider, Jeff Department of Machine Learning Carnegie Mellon University United States Robotics Institute Carnegie Mellon University United States

The problem of offline reinforcement learning focuses on learning a good policy from a log of environment interactions. Past efforts for developing algorithms in this area have revolved around introducing constraints to online reinforcement learning algorithms to ensure the actions of the learned policy are constrained to the logged data. In this work, we explore an alternative approach by planning on the fixed dataset directly. Specifically, we introduce an algorithm which forms a tabular Markov Decision Process (MDP) over the logged data by adding new transitions to the dataset. We do this by using learned dynamics models to plan short trajectories between states. Since exact value iteration can be performed on this constructed MDP, it becomes easy to identify which trajectories are advantageous to add to the MDP. Crucially, since most transitions in this MDP come from the logged data, trajectories from the MDP can be rolled out for long periods with confidence. We prove that this property allows one to make upper and lower bounds on the value function up to appropriate distance metrics. Finally, we demonstrate empirically how algorithms that uniformly constrain the learned policy to the entire dataset can result in unwanted behavior, and we show an example in which simply behavior cloning the optimal policy of the MDP created by our algorithm avoids this problem. Copyright © 2022, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Multi-modal NeRF Self-Supervision for LiDAR Semantic Segmentation

Multi-modal NeRF Self-Supervision for LiDAR Semantic Segment...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Xavier Timoneda Markus Herb Fabian Duerr Daniel Goehring Fisher Yu Onboard Fusion Team at CARIAD SE Volkswagen Group Ingolstadt Germany Dahlem Center for Machine Learning and Robotics Group at Freie Universität Berlin Germany Department of Information Technology and Electrical Engineering ETH Zurich Switzerland

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

LiDAR Semantic Segmentation is a fundamental task in autonomous driving perception consisting of associating each LiDAR point to a semantic label. Fully-supervised models have widely tackled this task, but they require labels for each scan, which either limits their domain or requires impractical amounts of expensive *** images, which are generally recorded alongside LiDAR pointclouds, can be processed by the widely available 2D foundation models, which are generic and dataset-agnostic. However, distilling knowledge from 2D data to improve LiDAR perception raises domain adaptation challenges. For example, the classical perspective projection suffers from the parallax effect produced by the position shift between both sensors at their respective capture *** propose a Semi-Supervised learning setup to leverage unlabeled LiDAR pointclouds alongside distilled knowledge from the camera images. To self-supervise our model on the unlabeled scans, we add an auxiliary NeRF head and cast rays from the camera viewpoint over the unlabeled voxel features. The NeRF head predicts densities and semantic logits at each sampled ray location which are used for rendering pixel semantics. Concurrently, we query the Segment-Anything (SAM) foundation model with the camera image to generate a set of unlabeled generic masks. We fuse the masks with the rendered pixel semantics from LiDAR to produce pseudo-labels that supervise the pixel predictions. During inference, we drop the NeRF head and run our model with only *** show the effectiveness of our approach in three public LiDAR Semantic Segmentation benchmarks: nuScenes, SemanticKITTI and ScribbleKITTI.

关键词： Laser radar Head Foundation models Semantic segmentation Semantics Benchmark testing Cameras Neural radiance field Rendering (computer graphics) Reliability

来源：评论

学校读者我要写书评

暂无评论

CITR: A Coordinate-Invariant Task Representation for Robotic Manipulation

CITR: A Coordinate-Invariant Task Representation for Robotic...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Peter So Rafael I. Cabral Muchacho Robin Jeanne Kirschner Abdalla Swikir Luis Figueredo Fares J. Abu-Dakka Sami Haddadin Munich Institute of Robotics and Machine Intelligence TUM Germany Division of Robotics Perception and Learning KTH Royal Institute of Technology Sweden Department of Electrical and Electronic Engineering Omar Al-Mukhtar University (OMU) Libya School of Computer Science University of Nottingham UK Electronic and Informatics Department Faculty of Engineering Mondragon Unibertsitatea Spain

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

The basis for robotics skill learning is an adequate representation of manipulation tasks based on their physical properties. As manipulation tasks are inherently invariant to the choice of reference frame, an ideal task representation would also exhibit this property. Nevertheless, most robotic learning approaches use unprocessed, coordinate-dependent robot state data for learning new skills, thus inducing challenges regarding the interpretability and transferability of the learned *** this paper, we propose a transformation from spatial measurements to a coordinate-invariant feature space, based on the pairwise inner product of the input measurements. We describe and mathematically deduce the concept, establish the task fingerprints as an intuitive image-based representation, experimentally collect task fingerprints, and demonstrate the usage of the representation for task classification. This representation motivates further research on data-efficient and transferable learning methods for online manipulation task classification and task-level perception.

关键词： learning systems Coordinate measuring machines Robot kinematics Taxonomy Fingerprint recognition Mathematical models Libraries

来源：评论

学校读者我要写书评

暂无评论

Wheel-GINS: A GNSS/INS Integrated Navigation System with a Wheel-mounted IMU

arXiv

引用

arXiv 2025年

作者： Wu, Yibin Kuang, Jian Niu, Xiaoji Stachniss, Cyrill Klingbeil, Lasse Kuhlmann, Heiner Center for Robotics Institute of Geodesy and Geoinformation University of Bonn Bonn Germany Department of Engineering Science University of Oxford United Kingdom Lamarr Institute for Machine Learning and Artificial Intelligence Germany GNSS Research Center Wuhan University Wuhan China

A long-term accurate and robust localization system is essential for mobile robots to operate efficiently outdoors. Recent studies have shown the significant advantages of the wheelmounted inertial measurement unit (Wheel-IMU)-based dead reckoning system. However, it still drifts over extended periods because of the absence of external correction signals. To achieve the goal of long-term accurate localization, we propose Wheel- GINS, a Global Navigation Satellite System (GNSS)/inertial navigation system (INS) integrated navigation system using a Wheel-IMU. Wheel-GINS fuses the GNSS position measurement with the Wheel-IMU via an extended Kalman filter to limit the long-term error drift and provide continuous state estimation when the GNSS signal is blocked. Considering the specificities of the GNSS/Wheel-IMU integration, we conduct detailed modeling and online estimation of the Wheel-IMU installation parameters, including the Wheel-IMU leverarm and mounting angle and the wheel radius error. Experimental results have shown that Wheel- GINS outperforms the traditional GNSS/Odometer/INS integrated navigation system during GNSS outages. At the same time, Wheel-GINS can effectively estimate the Wheel-IMU installation parameters online and, consequently, improve the localization accuracy and practicality of the system. The source code of our implementation is publicly available (https://***/i2Nav- WHU/Wheel-GINS). Copyright © 2025, The Authors. All rights reserved.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Guided Decoding for Robot On-line Motion Generation and Adaption

Guided Decoding for Robot On-line Motion Generation and Adap...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Nutan Chen Botond Cseke Elie Aljalbout Alexandros Paraschos Marvin Alles Patrick van der Smagt Machine Learning Research Lab Volkswagen Group Germany Department of Informatics Robotics and Perception Group University of Zurich (UZH) Department of Neuroinformatics UZH and ETH Zurich Switzerland Faculty of Informatics Eötvös Loránd University Budapest Hungary

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

We present a novel motion generation approach for robot arms, with high degrees of freedom, in complex settings that can adapt online to obstacles or new via points. learning from Demonstration facilitates rapid adaptation to new tasks and optimizes the utilization of accumulated expertise by allowing robots to learn and generalize from demonstrated trajectories. We train a transformer architecture, based on conditional variational autoencoder, on a large dataset of simulated trajectories used as demonstrations. Our architecture learns essential motion generation skills from these demonstrations and is able to adapt them to meet auxiliary tasks. Additionally, our approach implements auto-regressive motion generation to enable real-time adaptations, as, for example, introducing or changing via-points, and velocity and acceleration constraints. Using beam search, we present a method for further adaption of our motion generator to avoid obstacles. We show that our model successfully generates motion from different initial and target points and that is capable of generating trajectories that navigate complex tasks across different robotic platforms.

关键词： Robot motion Visualization Robot kinematics Humanoid robots Color Transformers Robustness Trajectory Decoding Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Functional TMS Mapping During Sensorimotor Integration Task 5

Functional TMS Mapping During Sensorimotor Integration Task

引用

5th International Conference Neurotechnologies and Neurointerfaces, CNN 2023

作者： Udoratina, Anna Grigorev, Nikita Savosenkov, Andrey Ermolaev, Denis Maksimenko, Vladimir Gordleeva, Susanna Lobachevsky State University of Nizhny Novgorod Neurotechnology Department Nizhny Novgorod Russia Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Lobachevsky State University of Nizhny Novgorod Mathematics and Mechanics Department Nizhny Novgorod Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia Neuroscience Research Institute Samara State Medical University Samara Russia

ISBN: (纸本)9798350344059

In the present research, we studied spatiotemporal influence of a single-pulse TMS on the process of sensorimotor integration. We considered how real and sham stimulation of the left or right premotor, motor or sensorimotor cortex, delivered 200 or 800 ms after the demonstration of a visual stimuli, affected response time of subjects during sensorimotor integration task. At this stage of the study, we found that a single TMS of the sensorimotor cortex, delivered 800 ms after stimulus presentation, increases response time. © 2023 IEEE.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Tree Instance Segmentation and Traits Estimation for Forestry Environments Exploiting LiDAR Data Collected by Mobile Robots

Tree Instance Segmentation and Traits Estimation for Forestr...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Meher V. R. Malladi Tiziano Guadagnino Luca Lobefaro Matias Mattamala Holger Griess Janine Schweier Nived Chebrolu Maurice Fallon Jens Behley Cyrill Stachniss Center for Robotics University of Bonn Germany University of Oxford UK Swiss Federal Institute for Forest Snow and Landscape Research Switzerland Department of Engineering Science University of Oxford UK Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Forests play a crucial role in our ecosystems, functioning as carbon sinks, climate stabilizers, biodiversity hubs, and sources of wood. By the very nature of their scale, monitoring and maintaining forests is a challenging task. robotics in forestry can have the potential for substantial automation toward efficient and sustainable foresting practices. In this paper, we address the problem of automatically producing a forest inventory by exploiting LiDAR data collected by a mobile platform. To construct an inventory, we first extract tree instances from point clouds. Then, we process each instance to extract forestry inventory information. Our approach provides the per-tree geometric trait of "diameter at breast height" together with the individual tree locations in a plot. We validate our results against manual measurements collected by foresters during field trials. Our experiments show strong segmentation and tree trait estimation performance, underlining the potential for automating forestry services. Results furthermore show a superior performance compared to the popular baseline methods used in this domain.

关键词： Instance segmentation Point cloud compression Forests Laser radar Pipelines Semantics Estimation

来源：评论

学校读者我要写书评

暂无评论

Multi-modal NeRF Self-Supervision for LiDAR Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Timoneda, Xavier Herb, Markus Duerr, Fabian Goehring, Daniel Yu, Fisher Onboard Fusion team at CARIAD SE Volkswagen Group Ingolstadt Germany Dahlem Center for Machine Learning and Robotics group Freie Universität Berlin Germany Department of Information Technology and Electrical Engineering ETH Zürich Switzerland

LiDAR Semantic Segmentation is a fundamental task in autonomous driving perception consisting of associating each LiDAR point to a semantic label. Fully-supervised models have widely tackled this task, but they require labels for each scan, which either limits their domain or requires impractical amounts of expensive annotations. Camera images, which are generally recorded alongside LiDAR pointclouds, can be processed by the widely available 2D foundation models, which are generic and dataset-agnostic. However, distilling knowledge from 2D data to improve LiDAR perception raises domain adaptation challenges. For example, the classical perspective projection suffers from the parallax effect produced by the position shift between both sensors at their respective capture times. We propose a Semi-Supervised learning setup to leverage unlabeled LiDAR pointclouds alongside distilled knowledge from the camera images. To self-supervise our model on the unlabeled scans, we add an auxiliary NeRF head and cast rays from the camera viewpoint over the unlabeled voxel features. The NeRF head predicts densities and semantic logits at each sampled ray location which are used for rendering pixel semantics. Concurrently, we query the Segment-Anything (SAM) foundation model with the camera image to generate a set of unlabeled generic masks. We fuse the masks with the rendered pixel semantics from LiDAR to produce pseudo-labels that supervise the pixel predictions. During inference, we drop the NeRF head and run our model with only LiDAR. We show the effectiveness of our approach in three public LiDAR Semantic Segmentation benchmarks: nuScenes, SemanticKITTI and ScribbleKITTI. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

One Policy to Run Them All: an End-to-end learning Approach to Multi-Embodiment Locomotion

arXiv

引用

arXiv 2024年

作者： Bohlinger, Nico Czechmanowski, Grzegorz Krupka, Maciej Kicki, Piotr Walas, Krzysztof Peters, Jan Tateo, Davide Department of Computer Science Technical University of Darmstadt Germany Institute of Robotics and Machine Intelligence Poznan University of Technology Poland Research Department: Systems AI for Robot Learning Germany IDEAS NCBR Warsaw Poland Hessian.AI Centre for Cognitive Science

Deep Reinforcement learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is still missing a single learning framework that can control all these different embodiments easily and effectively and possibly transfer, zero or few-shot, to unseen robot embodiments. We introduce URMA, the Unified Robot Morphology Architecture, to close this gap. Our framework brings the end-to-end Multi-Task Reinforcement learning approach to the realm of legged robots, enabling the learned policy to control any type of robot morphology. The key idea of our method is to allow the network to learn an abstract locomotion controller that can be seamlessly shared between embodiments thanks to our morphology-agnostic encoders and decoders. This flexible architecture can be seen as a potential first step in building a foundation model for legged robot locomotion. Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploration via planning for information about the optimal trajectory 22

Exploration via planning for information about the optimal t...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Viraj Mehta Ian Char Joseph Abbate Rory Conlin Mark D. Boyer Stefano Ermon Jeff Schneider Willie Neiswanger Robotics Institute Machine Learning Department Carnegie Mellon University Princeton University Princeton Plasma Physics Laboratory Computer Science Department Stanford University

ISBN: (纸本)9781713871088

Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or robotics, where executing a policy in the environment is costly. In popular RL algorithms, agents typically explore either by adding stochasticity to a reward-maximizing policy or by attempting to gather maximal information about environment dynamics without taking the given task into account. In this work, we develop a method that allows us to plan for exploration while taking both the task and the current knowledge about the dynamics into account. The key insight to our approach is to plan an action sequence that maximizes the expected information gain about the optimal trajectory for the task at hand. We demonstrate that our method learns strong policies with 2x fewer samples than strong exploration baselines and 200x fewer samples than model free methods on a diverse set of low-to-medium dimensional control tasks in both the open-loop and closed-loop control settings.

关键词：

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：