Autonomous Robots最新文献_第5页

Reinforcement learning for shared autonomy drone landings 共享自主无人机着陆的强化学习

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-10-21 DOI: 10.1007/s10514-023-10143-3

Kal Backman, Dana Kulić, Hoam Chung

{"title":"Reinforcement learning for shared autonomy drone landings","authors":"Kal Backman, Dana Kulić, Hoam Chung","doi":"10.1007/s10514-023-10143-3","DOIUrl":"10.1007/s10514-023-10143-3","url":null,"abstract":"<div><p>Novice pilots find it difficult to operate and land unmanned aerial vehicles (UAVs), due to the complex UAV dynamics, challenges in depth perception, lack of expertise with the control interface and additional disturbances from the ground effect. Therefore we propose a shared autonomy approach to assist pilots in safely landing a UAV under conditions where depth perception is difficult and safe landing zones are limited. Our approach is comprised of two modules: a perception module that encodes information onto a compressed latent representation using two RGB-D cameras and a policy module that is trained with the reinforcement learning algorithm TD3 to discern the pilot’s intent and to provide control inputs that augment the user’s input to safely land the UAV. The policy module is trained in simulation using a population of simulated users. Simulated users are sampled from a parametric model with four parameters, which model a pilot’s tendency to conform to the assistant, proficiency, aggressiveness and speed. We conduct a user study (<span>(n=28)</span>) where human participants were tasked with landing a physical UAV on one of several platforms under challenging viewing conditions. The assistant, trained with only simulated user data, improved task success rate from 51.4 to 98.2% despite being unaware of the human participants’ goal or the structure of the environment a priori. With the proposed assistant, regardless of prior piloting experience, participants performed with a proficiency greater than the most experienced unassisted participants.\u0000</p></div>","PeriodicalId":55409,"journal":{"name":"Autonomous Robots","volume":"47 8","pages":"1419 - 1438"},"PeriodicalIF":3.5,"publicationDate":"2023-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10514-023-10143-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135510764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Reinforcement learning with model-based feedforward inputs for robotic table tennis 基于模型前馈输入的乒乓球机器人强化学习

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-10-17 DOI: 10.1007/s10514-023-10140-6

Hao Ma, Dieter Büchler, Bernhard Schölkopf, Michael Muehlebach

{"title":"Reinforcement learning with model-based feedforward inputs for robotic table tennis","authors":"Hao Ma, Dieter Büchler, Bernhard Schölkopf, Michael Muehlebach","doi":"10.1007/s10514-023-10140-6","DOIUrl":"10.1007/s10514-023-10140-6","url":null,"abstract":"<div><p>We rethink the traditional reinforcement learning approach, which is based on optimizing over feedback policies, and propose a new framework that optimizes over feedforward inputs instead. This not only mitigates the risk of destabilizing the system during training but also reduces the bulk of the learning to a supervised learning task. As a result, efficient and well-understood supervised learning techniques can be applied and are tuned using a validation data set. The labels are generated with a variant of iterative learning control, which also includes prior knowledge about the underlying dynamics. Our framework is applied for intercepting and returning ping-pong balls that are played to a four-degrees-of-freedom robotic arm in real-world experiments. The robot arm is driven by pneumatic artificial muscles, which makes the control and learning tasks challenging. We highlight the potential of our framework by comparing it to a reinforcement learning approach that optimizes over feedback policies. We find that our framework achieves a higher success rate for the returns (<span>(100%)</span> vs. <span>(96%)</span>, on 107 consecutive trials, see https://youtu.be/kR9jowEH7PY) while requiring only about one tenth of the samples during training. We also find that our approach is able to deal with a variant of different incoming trajectories.\u0000</p></div>","PeriodicalId":55409,"journal":{"name":"Autonomous Robots","volume":"47 8","pages":"1387 - 1403"},"PeriodicalIF":3.5,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10514-023-10140-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135995053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

UVS: underwater visual SLAM—a robust monocular visual SLAM system for lifelong underwater operations UVS:水下视觉SLAM -一个强大的单目视觉SLAM系统，用于终身水下操作

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-09-22 DOI: 10.1007/s10514-023-10138-0

Marco Leonardi, Annette Stahl, Edmund Førland Brekke, Martin Ludvigsen

{"title":"UVS: underwater visual SLAM—a robust monocular visual SLAM system for lifelong underwater operations","authors":"Marco Leonardi, Annette Stahl, Edmund Førland Brekke, Martin Ludvigsen","doi":"10.1007/s10514-023-10138-0","DOIUrl":"10.1007/s10514-023-10138-0","url":null,"abstract":"<div><p>In this paper, a visual simultaneous localization and mapping (VSLAM/visual SLAM) system called underwater visual SLAM (UVS) system is presented, specifically tailored for camera-only navigation in natural underwater environments. The UVS system is particularly optimized towards precision and robustness, as well as lifelong operations. We build upon Oriented features from accelerated segment test and Rotated Binary robust independent elementary features simultaneous localization and mapping (ORB-SLAM) and improve the accuracy by performing an exact search in the descriptor space during triangulation and the robustness by utilizing a unified initialization method and a motion model. In addition, we present a scale-agnostic station-keeping detection, which aims to optimize the map and poses during station-keeping, and a pruning strategy, which takes into account the point’s age and distance to the active keyframe. An exhaustive evaluation is presented to the reader, using a total of 38 in-air and underwater sequences.\u0000</p></div>","PeriodicalId":55409,"journal":{"name":"Autonomous Robots","volume":"47 8","pages":"1367 - 1385"},"PeriodicalIF":3.5,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10514-023-10138-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136015937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sim-to-real transfer of co-optimized soft robot crawlers 协同优化软机器人履带的模拟到真实迁移

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-09-08 DOI: 10.1007/s10514-023-10130-8

Charles Schaff, Audrey Sedal, Shiyao Ni, Matthew R. Walter

引用次数: 0

Learning modular language-conditioned robot policies through attention 通过注意力学习模块化语言条件机器人策略

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-08-30 DOI: 10.1007/s10514-023-10129-1

Yifan Zhou, Shubham Sonawani, Mariano Phielipp, Heni Ben Amor, Simon Stepputtis

引用次数: 1

Integrating action knowledge and LLMs for task planning and situation handling in open worlds 整合行动知识和法学硕士在开放世界的任务规划和情况处理

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-08-29 DOI: 10.1007/s10514-023-10133-5

Yan Ding, Xiaohan Zhang, Saeid Amiri, Nieqing Cao, Hao Yang, Andy Kaminski, Chad Esselink, Shiqi Zhang

{"title":"Integrating action knowledge and LLMs for task planning and situation handling in open worlds","authors":"Yan Ding, Xiaohan Zhang, Saeid Amiri, Nieqing Cao, Hao Yang, Andy Kaminski, Chad Esselink, Shiqi Zhang","doi":"10.1007/s10514-023-10133-5","DOIUrl":"10.1007/s10514-023-10133-5","url":null,"abstract":"<div><p>Task planning systems have been developed to help robots use human knowledge (about actions) to complete long-horizon tasks. Most of them have been developed for “closed worlds” while assuming the robot is provided with complete world knowledge. However, the real world is generally open, and the robots frequently encounter unforeseen situations that can potentially break theplanner’s completeness. Could we leverage the recent advances on pre-trained Large Language Models (LLMs) to enable classical planning systems to deal with novel situations? This paper introduces a novel framework, called COWP, for open-world task planning and situation handling. COWP dynamically augments the robot’s action knowledge, including the preconditions and effects of actions, with task-oriented commonsense knowledge. COWP embraces the openness from LLMs, and is grounded to specific domains via action knowledge. For systematic evaluations, we collected a dataset that includes 1085 execution-time situations. Each situation corresponds to a state instance wherein a robot is potentially unable to complete a task using a solution that normally works. Experimental results show that our approach outperforms competitive baselines from the literature in the success rate of service tasks. Additionally, we have demonstrated COWP using a mobile manipulator. Supplementary materials are available at: https://cowplanning.github.io/</p></div>","PeriodicalId":55409,"journal":{"name":"Autonomous Robots","volume":"47 8","pages":"981 - 997"},"PeriodicalIF":3.5,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136248667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

ProgPrompt: program generation for situated robot task planning using large language models ProgPrompt:使用大型语言模型生成定位机器人任务规划的程序

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-08-28 DOI: 10.1007/s10514-023-10135-3

Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, Animesh Garg

{"title":"ProgPrompt: program generation for situated robot task planning using large language models","authors":"Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, Animesh Garg","doi":"10.1007/s10514-023-10135-3","DOIUrl":"10.1007/s10514-023-10135-3","url":null,"abstract":"<div><p>Task planning can require defining myriad domain knowledge about the world in which a robot needs to act. To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information. However, such methods either require enumerating all possible next steps for scoring, or generate free-form text that may contain actions not possible on a given robot in its current context. We present a programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks. Our key insight is to prompt the LLM with program-like specifications of the available actions and objects in an environment, as well as with example <span>programs</span> that can be executed. We make concrete recommendations about prompt structure and generation constraints through ablation experiments, demonstrate state of the art success rates in VirtualHome household tasks, and deploy our method on a physical robot arm for tabletop tasks. Website and code at progprompt.github.io</p></div>","PeriodicalId":55409,"journal":{"name":"Autonomous Robots","volume":"47 8","pages":"999 - 1012"},"PeriodicalIF":3.5,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10514-023-10135-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48320797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

Learning scalable and efficient communication policies for multi-robot collision avoidance 学习可扩展且高效的多机器人防撞通信策略

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-08-19 DOI: 10.1007/s10514-023-10127-3

Álvaro Serra-Gómez, Hai Zhu, Bruno Brito, Wendelin Böhmer, Javier Alonso-Mora

{"title":"Learning scalable and efficient communication policies for multi-robot collision avoidance","authors":"Álvaro Serra-Gómez, Hai Zhu, Bruno Brito, Wendelin Böhmer, Javier Alonso-Mora","doi":"10.1007/s10514-023-10127-3","DOIUrl":"10.1007/s10514-023-10127-3","url":null,"abstract":"<div><p>Decentralized multi-robot systems typically perform coordinated motion planning by constantly broadcasting their intentions to avoid collisions. However, the risk of collision between robots varies as they move and communication may not always be needed. This paper presents an efficient communication method that addresses the problem of “when” and “with whom” to communicate in multi-robot collision avoidance scenarios. In this approach, each robot learns to reason about other robots’ states and considers the risk of future collisions before asking for the trajectory plans of other robots. We introduce a new neural architecture for the learned communication policy which allows our method to be scalable. We evaluate and verify the proposed communication strategy in simulation with up to twelve quadrotors, and present results on the zero-shot generalization/robustness capabilities of the policy in different scenarios. We demonstrate that our policy (learned in a simulated environment) can be successfully transferred to real robots.\u0000</p></div>","PeriodicalId":55409,"journal":{"name":"Autonomous Robots","volume":"47 8","pages":"1275 - 1297"},"PeriodicalIF":3.5,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10514-023-10127-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46045076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Humans as path-finders for mobile robots using teach-by-showing navigation 人类作为移动机器人的寻路者，使用指示式导航

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-08-17 DOI: 10.1007/s10514-023-10125-5

Alessandro Antonucci, Paolo Bevilacqua, Stefano Leonardi, Luigi Paolopoli, Daniele Fontanelli

引用次数: 0

Design and control of BRAVER: a bipedal robot actuated via proprioceptive electric motors 本体感觉电机驱动的两足机器人BRAVER的设计与控制

IF 3.5 3区计算机科学

Autonomous Robots Pub Date : 2023-07-23 DOI: 10.1007/s10514-023-10117-5

Zhengguo Zhu, Weiliang Zhu, Guoteng Zhang, Teng Chen, Yibin Li, Xuewen Rong, Rui Song, Daoling Qin, Qiang Hua, Shugen Ma

引用次数: 1