检索结果-内蒙古大学图书馆

American Control Conference (ACC)

作者： H. Siming Christopher D. Hsu Dexter Ong Yifei Simon Shao Pratik Chaudhari General Robotics Automation Sensing and Perception (GRASP) Laboratory University of Pennsylvania

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

We study active perception from first principles to argue that an autonomous agent performing active perception should maximize the mutual information that past observations posses about future ones. Doing so requires (a) a representation of the scene that summarizes past observations and the ability to update this representation to incorporate new observations (state estimation and mapping), (b) the ability to synthesize new observations of the scene (a generative model), and (c) the ability to select control trajectories that maximize predictive information (planning). This motivates a neural radiance field (NeRF)-like representation which captures photometric, geometric and semantic properties of the scene grounded. This representation is well-suited to synthesizing new observations from different viewpoints. And thereby, a sampling-based planner can be used to calculate the predictive information from synthetic observations along dynamically-feasible trajectories. We use active perception for exploring cluttered indoor environments and employ a notion of semantic uncertainty to check for the successful completion of an exploration task. We demonstrate these ideas via simulation in realistic 3D indoor environments 1 1 Code is available at https://***/grasp-1yd/Active-perception-using-Neural-Radiance-Fields. Full manuscript is available at https://***/abs/2310.09892.

关键词： Uncertainty Three-dimensional displays Semantics Active perception Predictive models Neural radiance field Trajectory

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Reduced-order Models of Legged Robots

Reinforcement Learning for Reduced-order Models of Legged Ro...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Yu-Ming Chen Hien Bui Michael Posa General Robotics Automation Sensing and Perception (GRASP) Laboratory University of Pennsylvania Philadelphia PA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Model-based approaches for planning and control for bipedal locomotion have a long history of success. It can provide stability and safety guarantees while being effective in accomplishing many locomotion tasks. Model-free reinforcement learning, on the other hand, has gained much popularity in recent years due to computational advancements. It can achieve high performance in specific tasks, but it lacks physical interpretability and flexibility in re-purposing the policy for a different set of tasks. For instance, we can initially train a neural network (NN) policy using velocity commands as inputs. However, to handle new task commands like desired hand or footstep locations at a desired walking velocity, we must retrain a new NN policy. In this work, we attempt to bridge the gap between these two bodies of work on a bipedal platform. We formulate a model-based reinforcement learning problem to learn a reduced-order model (ROM) within a model predictive control (MPC). Results show a 49% improvement in viable task region size and a 21% reduction in motor torque cost. All videos and code are available at https://***/view/ymchen/research/rl-for-roms.

关键词： Legged locomotion Torque Computational modeling Reinforcement learning Artificial neural networks Reduced order systems Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Active Scout: Multi-Target Tracking Using Neural Radiance Fields in Dense Urban Environments

Active Scout: Multi-Target Tracking Using Neural Radiance Fi...

引用

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

作者： Christopher D. Hsu Pratik Chaudhari DEVCOM Army Research Laboratory Department of Electrical & Systems Engineering and General Robotics Automation Sensing and Perception (GRASP) Laboratory University of Pennsylvania

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

We study pursuit-evasion games in highly occluded urban environments, e.g. tall buildings in a city, where a scout (quadrotor) tracks multiple dynamic targets on the ground. We show that we can build a neural radiance field (NeRF) representation of the city—online—using RGB and depth images from different vantage points. This representation is used to calculate the information gain to both explore unknown parts of the city and track the targets—thereby giving a completely first-principles approach to actively tracking dynamic targets. We demonstrate, using a custom-built simulator using Open Street Maps data of Philadelphia and New York City, that we can explore and locate 20 stationary targets within 300 steps. This is slower than a greedy baseline, which does not use active perception. But for dynamic targets that actively hide behind occlusions, we show that our approach maintains, at worst, a tracking error of 200m; the greedy baseline can have a tracking error as large as 600m. We observe a number of interesting properties in the scout’s policies, e.g., it switches its attention to track a different target periodically, as the quality of the NeRF representation improves over time, the scout also becomes better in terms of target tracking.

关键词： Target tracking Urban areas Buildings Games Neural radiance field Information filters Probabilistic logic Mutual information Intelligent robots Quadrotors

来源：评论

学校读者我要写书评

暂无评论

Online Optimization of Soft Manipulator Mechanics via Hierarchical Control

Online Optimization of Soft Manipulator Mechanics via Hierar...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Shivangi Misra Cynthia Sung General Robotics Automation Sensing & Perception (GRASP) Lab University of Pennsylvania Philadelphia PA USA

Actively tuning mechanical properties in soft robots is now feasible due to advancements in soft actuation technologies. In soft manipulators, these novel actuators can be distributed over the robot body to allow greater control over its large number of degrees of freedom and to stabilize local deformations against a range of disturbances. In this paper, we present a hierarchical policy for stiffness control for such a class of soft manipulators. The stiffness changes induce desired deformations in each segment, thereby influencing the manipulator's end-effector position. The algorithm can be run as an online controller to influence the manipulator's stable states – as we demonstrate in simulation – or offline as a design algorithm to optimize stiffness distributions – as we showcase in a hardware demonstration. Our proposed hierarchical control scheme is agnostic to the stiffness actuation method and can extend to other soft manipulators with nonuniform stiffness distributions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Characterization of a Pneumatic Tunable-Stiffness Bellows Actuator

Design and Characterization of a Pneumatic Tunable-Stiffness...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Rongqian Chen Jun Kwon Wei-Hsi Chen Cynthia Sung General Robotics Automation Sensing & Perception (GRASP) Lab University of Pennsylvania Philadelphia PA USA

We introduce a self-contained pneumatic actuator capable of 1.43 times stiffness gain from 1332 N/m to 1913 N/m without needing an external air source or valve. The design incorporates an air chamber bellows and a spring bellows, connected and sealed. Stiffness modulation is achieved by altering the air chamber volume. We present an approach for computing the volume, pressurized force, and stiffness of a single bellows component, as well as methods for composing single bellows models to predict the change in stiffness of the dual bellows actuator as a function of air chamber compression. We detail the fabrication of the actuator and verify the models on the fabricated prototype. This actuator holds promise for future integration in tunable stiffness robots demanding high strength and adaptability in dynamic scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point2Point: A Framework for Efficient Deep Learning on Hilbert Sorted Point Clouds with Applications in Spatio-Temporal Occupancy Prediction

Point2Point: A Framework for Efficient Deep Learning on Hilb...

引用

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

作者： Athrva Atul Pandhare General Robotics Automation Sensing & Perception Lab (GRASP) University of Pennsylvania PA USA

The irregularity and permutation invariance of point cloud data pose challenges for effective learning. Conventional methods for addressing this issue involve converting raw point clouds to intermediate representations such as 3D voxel grids or range images. While such intermediate representations solve the problem of permutation invariance, they can result in significant loss of information. Approaches that do learn on raw point clouds either have trouble in resolving neighborhood relationships between points or are too complicated in their formulation. In this paper, we propose a novel approach to representing point clouds as a locality preserving 1D ordering induced by the Hilbert space-filling curve. We also introduce Point2Point, a neural architecture that can effectively learn on Hilbert-sorted point clouds. We show that Point2Point shows competitive performance on point cloud segmentation and generation tasks. Finally, we show the performance of Point2Point on Spatio-temporal Occupancy prediction from Point clouds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Opportunistic Communication in Robot Teams

Opportunistic Communication in Robot Teams

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Daniel Mox Kashish Garg Alejandro Ribeiro Vijay Kumar General Robotics Automation Sensing and Perception (GRASP) Laboratory University of Pennsylvania Philadelphia PA USA Electrical and Systems Engineering Department University of Pennsylvania Philadelphia PA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In this paper we present a new approach to Mobile Infrastructure on Demand (MID) where a dedicated team of robots creates and sustains a wireless network that satisfies the communication requirements of a different team of task-oriented robots seeking to coordinate their actions in the absence of existing communication infrastructure. Different from previous works, our approach forgoes heuristics for network performance such as algebraic-connectivity or network flow optimizations and instead positions communication support robots to directly maximize the probability of packet delivery by the underlying opportunistic routing protocol. Our system is task agnostic and practical to implement and operate on robots equipped with off-the-shelf WiFi radios. We demonstrate this through a set of experiments showing our MID system maintaining the delivery of critical mission data in a situational awareness setting and enabling foraging robots to effectively coordinate their actions during multi-robot exploration.

关键词： Robot kinematics Wireless networks Routing protocols Mobile robots Communication networks Task analysis Robots

来源：评论

学校读者我要写书评

暂无评论

Local Input-to-State Stability for Consensus in the Presence of Intermittent Communication and Input Saturation

Local Input-to-State Stability for Consensus in the Presence...

引用

IEEE Conference on Decision and Control

作者： Thales C. Silva M. Ani Hsieh General Robotics Actuation Sensing and Perception (GRASP) Laboratory University of Pennsylvania Philadelphia PA USA

This paper addresses the problem of reaching con-sensus under input saturation and intermittent communication, which can hinder the convergence of the system. We propose a method that translates the consensus into an equivalent stability problem. Then, we compute bounded sets that enclose the initial conditions and the evolution of trajectories leading to local input-to-state stability for systems interconnected over directed intermittent topologies. Our contributions include sufficient conditions for stability and stabilization of multi-agent systems under intermittent interactions and saturating inputs, with the ability to evaluate disturbance tolerance and rejection based on the regions that enclose the system's trajectories. We define disturbance rejection in terms of the $\mathscr{L}_{2}$ gain, and formulate stability and controller design conditions as convex optimization problems. Our method enable the maximization of regions that ensure local input-to-state stability, we provide numerical examples highlighting the tradeoffs between mean frequency of intermittent interactions, disturbance energy, and convergence region size.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reparametrization of 3D CSC Dubins Paths Enabling 2D Search

arXiv

引用

arXiv 2025年

作者： Xu, Ling Baryshnikov, Yuliy Sung, Cynthia General Robotics Automation Sensing & Perception Lab University of Pennsylvania PhiladelphiaPA United States Department of Mathematics University of Illinois Urbana-Champaign UrbanaIL United States

This paper addresses the Dubins path planning problem for vehicles in 3D space. In particular, we consider the problem of computing CSC paths – paths that consist of a circular arc (C) followed by a straight segment (S) followed by a circular arc (C). These paths are useful for vehicles such as fixed-wing aircraft and underwater submersibles that are subject to lower bounds on turn radius. We present a new parameterization that reduces the 3D CSC planning problem to a search over 2 variables, thus lowering search complexity, while also providing gradients that assist that search. We use these equations with a numerical solver to explore numbers and types of solutions computed for a variety of planar and 3D scenarios. Our method successfully computes CSC paths for the large majority of test cases, indicating that it could be useful for future generation of robust, efficient curvature-constrained trajectories. Copyright © 2025, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Designing 3D-printed concrete structures with scaled fabrication models

引用

Architectural Intelligence 2024年第1期3卷 1-16页

作者： Zhi, Yefan Teng, Teng Akbarzadeh, Masoud Polyhedral Structures Laboratory School of Design University of Pennsylvania Philadelphia USA Automation Sensing and Perception (GRASP) Lab School of Engineering and Applied Science General Robotic UniversityofPennsylvania Philadelphia USA

This article proposes using scaled fabrication models to assist the design research of 3D-printed discrete concrete structures where full-scale fabrication tests are costly and time-consuming. A scaled fabrication model (SFM) is a scaled model 3D-printed the same way as in actual construction to reflect its fabrication details and acquire alike layer line textures. The components of a 1:10 SFM can be eas- ily produced by consumer-level desktop 3D printers with minimal modification. SFMs assist the design communication and make possible quick tests of dis- tinct fabrication designs that are hard to assess in digital modeling [Response to 1.1] during the conceptual design phase. A case study of a discrete compression- dominant funicular floor derived from graphic statics is presented to illustrate the contribution of SFM to the design research of force-informed toolpathing where the printing direction of a component is aligned to the principal stress line. The design iterations encompass a sequence of component, partial, and full model SFM printing tests to explore and optimize the fabrication schemes where par- allel, non-parallel, and creased slicing methods to create toolpaths are compared and chosen to adapt different discrete components.

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：