检索结果-内蒙古大学图书馆

Towards Safe and Efficient Through-the-Canopy Autonomous Fruit Counting with UAVs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Teaya Ibrahimov, Roman Mueller, Mark W. The High Performance Robotics Lab Department of Mechanical Engineering University of California BerkeleyCA94709 United States

We present an autonomous aerial system for safe and efficient through-the-canopy fruit counting. Aerial robot applications in large-scale orchards face significant challenges due to the complexity of fine-tuning flight paths based on orchard layouts, canopy density, and plant variability. Through-the-canopy navigation is crucial for minimizing occlusion by leaves and branches but is more challenging due to the complex and dense environment compared to traditional over-the-canopy flights. Our system addresses these challenges by integrating: i) a high-fidelity simulation framework for optimizing flight trajectories, ii) a low-cost autonomy stack for canopy-level navigation and data collection, and iii) a robust workflow for fruit detection and counting using RGB images. We validate our approach through fruit counting with canopy-level aerial images and by demonstrating the autonomous navigation capabilities of our experimental vehicle. Copyright © 2024, The Authors. All rights reserved.

关键词： Orchards

Development of a Multi-Fingered Soft Gripper Digital Twin for Machine Learning-based Underactuated Control

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Wu-Te Lin, Pei-Chun University of California Berkeley United States Department of Mechanical Engineering National Taiwan University Bio-inspired Robotics Lab Taipei Taiwan

Soft robots, made from compliant materials, exhibit complex dynamics due to their flexibility and high degrees of freedom. Controlling soft robots presents significant challenges, particularly underactuation, where the number of inputs is fewer than the degrees of freedom. This research aims to develop a digital twin for multi-fingered soft grippers to advance the development of underactuation algorithms. The digital twin is designed to capture key effects observed in soft robots, such as nonlinearity, hysteresis, uncertainty, and time-varying phenomena, ensuring it closely replicates the behavior of a real-world soft gripper. Uncertainty is simulated using the Monte Carlo method. With the digital twin, a Q-learning algorithm is preliminarily applied to identify the optimal motion speed that minimizes uncertainty caused by the soft robots. Underactuated motions are successfully simulated within this environment. This digital twin paves the way for advanced machine learning algorithm training. © 2025, CC BY-NC-ND.

关键词： Degrees of freedom (mechanics)

Det-Recon-Reg: An Intelligent Framework Towards Automated Large-Scale Infrastructure Inspection

学校读者我要写书评

暂无评论

Det-Recon-Reg: An Intelligent Framework Towards Automated La...

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

作者： Guidong Yang Jihan Zhang Benyun Zhao Chuanxiang Gao Yijun Huang Junjie Wen Qingxiang Li Jerry Tang Xi Chen Ben M. Chen Department of Mechanical and Automation Engineering The Chinese University of Hong Kong (CUHK) Hong Kong Department of Mechanical Engineering High Performance Robotics Lab University of California Berkeley USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Visual inspection plays a predominant role in inspecting infrastructure surface. However, the generalization of existing visual inspection systems to large-scale real-world scenes remains challenging. In this paper, we introduce Det-Recon-Reg, an intelligent framework separating the complex inspection procedure into three stages: Detect, Reconstruct, and Register. (1) For defect detection (Detect), we present the first high-resolution defect dataset tailored for large-scale defect detection. Based on the dataset, we evaluate the most effective real-time object detection algorithms and push the boundary by proposing CUBIT-Net for real-world defect inspection. (2) For infrastructure reconstruction (Reconstruct), we propose a learning-based multi-view stereo (MVS) network to adapt to large-scale scenes, taking as input the multi-view images and outputting the point cloud reconstruction, where its performance has been validated on the standard MVS datasets, including BlendedMVS, DTU, and Tanks and Temples datasets. (3) For defect localization (Register), we propose an effective registration method based on the geographic information system that registers the detected defects onto the reconstructed infrastructure model to establish a global reference for maintenance measures. The real-world experiments further verify the effectiveness and efficiency of our proposed framework. More details about our proposed dataset, code, and appendix are available on our project page: https://***/large-scale-inspect-framework/.

关键词： Location awareness Point cloud compression Surface reconstruction Scalability Inspection Real-time systems Registers Image reconstruction Standards Defect detection

A Learning-based Quadcopter Controller with Extreme Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Dingqi Loquercio, Antonio Tang, Jerry Wang, Ting-Hao Malik, Jitendra Mueller, Mark W. High Performance Robotics Lab Dept. of Mechanical Engineering UC Berkeley United States The University of Pennsylvania United States Dept. of Electrical Engineering and Computer Science University of California at Berkeley United States

This paper introduces a learning-based low-level controller for quadcopters, which adaptively controls quadcopters with significant variations in mass, size, and actuator capabilities. Our approach leverages a combination of imitation learning and reinforcement learning, creating a fast-adapting and general control framework for quadcopters that eliminates the need for precise model estimation or manual tuning. The controller estimates a latent representation of the vehicle’s system parameters from sensor-action history, enabling it to adapt swiftly to diverse dynamics. Extensive evaluations in simulation demonstrate the controller’s ability to generalize to unseen quadcopter parameters, with an adaptation range up to 16 times broader than the training set. In real-world tests, the controller is successfully deployed on quadcopters with mass differences of 3.7 times and propeller constants varying by more than 100 times, while also showing rapid adaptation to disturbances such as off-center payloads and motor failures. These results highlight the potential of our controller to simplify the design process and enhance the reliability of autonomous drone operations in unpredictable environments. Video and code are at: https://***/muellerlab/xadapt_ctrl © 2024, CC BY.

关键词： Reinforcement learning

Learning a Single Near-hover Position Controller for Vastly Different Quadcopters

学校读者我要写书评

暂无评论

Learning a Single Near-hover Position Controller for Vastly ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Dingqi Zhang Antonio Loquercio Xiangyu Wu Ashish Kumar Jitendra Malik Mark W. Mueller Dept. of Mechanical Engineering High Performance Robotics Lab Dept. of Electrical Engineering and Computer Science University of California Berkeley

This paper proposes an adaptive near-hover position controller for quadcopters, which can be deployed to quadcopters of very different mass, size and motor constants, and also shows rapid adaptation to unknown disturbances during runtime. The core algorithmic idea is to learn a single policy that can adapt online at test time not only to the disturbances applied to the drone, but also to the robot dynamics and hardware in the same framework. We achieve this by training a neural network to estimate a latent representation of the robot and environment parameters, which is used to condition the behaviour of the controller, also represented as a neural network. We train both networks exclusively in simulation with the goal of flying the quadcopters to goal positions and avoiding crashes to the ground. We directly deploy the same controller trained in the simulation without any modifications on two quadcopters in the real world with differences in mass, size, motors, and propellers with mass differing by 4.5 times. In addition, we show rapid adaptation to sudden and large disturbances up to one-third of the mass of the quadcopters. We perform an extensive evaluation in both simulation and the physical world, where we outperform a state-of-the-art learning-based adaptive controller and a traditional PID controller specifically tuned to each platform individually. Video results can be found at https://***/U-c-LbTfvoA.

关键词：

Position: Social Choice Should Guide AI Alignment in Dealing with Diverse human Feedback 41

学校读者我要写书评

暂无评论

Position: Social Choice Should Guide AI Alignment in Dealing...

41st International Conference on Machine Learning, ICML 2024

作者： Conitzer, Vincent Freedman, Rachel Heitzig, Jobst Holliday, Wesley H. Jacobs, Bob M. Lambert, Nathan Mossé, Milan Pacuit, Eric Russell, Stuart Schoelkopf, Hailey Tewolde, Emanuel Zwicker, William S. Foundations of Cooperative AI Lab Computer Science Department Carnegie Mellon University Pittsburgh United States Institute for Ethics in AI University of Oxford Oxford United Kingdom Center for Human-Compatible AI Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Potsdam Institute for Climate Impact Research Brandenburg Potsdam Germany Department of Philosophy University of California Berkeley United States Department of Philosophy and Moral Sciences Ghent University Ghent Belgium Allen Institute for AI BerkeleyCA United States Department of Philosophy University of Maryland College Park United States EleutherAI United States Department of Mathematics Union College Schenectady United States Murat Sertel Center for Advanced Economic Studies Istanbul Bilgi University Istanbul Turkey

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about "collective" preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in berkeley, CA, USA in December 2023. Copyright 2024 by the author(s)

关键词： Reinforcement learning

Learning a Single Near-hover Position Controller for Vastly Different Quadcopters

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Dingqi Loquercio, Antonio Wu, Xiangyu Kumar, Ashish Malik, Jitendra Mueller, Mark W. High Performance Robotics Lab Dept. of Mechanical Engineering Dept. of Electrical Engineering and Computer Science University of California Berkeley United States

关键词： Controllers

The Feasibility of Constrained Reinforcement Learning Algorithms: A Tutorial Study

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Yujie Zheng, Zhilong Li, Shengbo Eben Tomizuka, Masayoshi Liu, Changliu School of Vehicle and Mobility State Key Lab of Intelligent Green Vehicle and Mobility Tsinghua University Beijing100084 China Department of Mechanical Engineering University of California BerkeleyCA94720 United States Robotics Institute Carnegie Mellon University PittsburghPA15289 United States

Satisfying safety constraints is a priority concern when solving optimal control problems (OCPs). Due to the existence of infeasibility phenomenon, where a constraint-satisfying solution cannot be found, it is necessary to identify a feasible region before implementing a policy. Existing feasibility theories built for model predictive control (MPC) only consider the feasibility of optimal policy, since MPC itself can be viewed as an optimal controller that solves an optimal action at every step. However, reinforcement learning (RL), as another important control method, solves the optimal policy in an iterative manner, which comes with a series of non-optimal intermediate policies. Feasibility analysis of these non-optimal policies is also necessary for iteratively improving constraint satisfaction;but that is not available under existing MPC feasibility theories. This paper proposes a feasibility theory that applies to both MPC and RL by filling in the missing part of feasibility analysis for an arbitrary policy. The basis of our theory is to decouple policy solving and implementation into two temporal domains: virtual-time domain and real-time domain. This allows us to separately define initial and endless, state and policy feasibility, and their corresponding feasible regions. Based on these definitions, we analyze the containment relationships between different feasible regions, which enables us to describe the feasible region of an arbitrary policy. We further provide virtual-time constraint design rules along with a practical design tool called feasibility function that helps to achieve the maximum feasible region. The feasibility function either represents a control invariant set or aggregates infinite steps of constraints into a single one. We review most of existing constraint formulations and point out that they are essentially applications of feasibility functions in different forms. We demonstrate our feasibility theory by visualizing different feasible r

关键词： Model predictive control

Towards Robots that Influence humans over Long-Term Interaction

学校读者我要写书评

暂无评论

Towards Robots that Influence Humans over Long-Term Interact...

IEEE International Conference on robotics and Automation (ICRA)

作者： Shahabedin Sagheb Ye-Ji Mun Neema Ahmadian Benjamin A. Christie Andrea Bajcsy Katherine Driggs-Campbell Dylan P. Losey Dept. of Mechanical Engineering Collaborative Robotics Lab (Collab) Virginia Tech Blacksburg VA Dept. of Electrical and Computer Engineering Human-Centered Autonomy Lab (HCAL) University of Illinois Urbana-Champaign IL Dept. of Electrical Engineering and Computer Science UC Berkeley CA

When humans interact with robots influence is inevitable. Consider an autonomous car driving near a human: the speed and steering of the autonomous car will affect how the human drives. Prior works have developed frameworks that enable robots to influence humans towards desired behaviors. But while these approaches are effective in the short-term (i.e., the first few human-robot interactions), here we explore long-term influence (i.e., repeated interactions between the same human and robot). Our central insight is that humans are dynamic: people adapt to robots, and behaviors which are influential now may fall short once the human learns to anticipate the robot's actions. With this insight, we experimentally demonstrate that a prevalent game-theoretic formalism for generating influential robot behaviors becomes less effective over repeated interactions. Next, we propose three modifications to Stackelberg games that make the robot's policy both influential and unpredictable. We finally test these modifications across simulations and user studies: our results suggest that robots which purposely make their actions harder to anticipate are better able to maintain influence over long-term interaction. See videos here: https://***/ydO83cgjZ2Q

关键词：