检索结果-内蒙古大学图书馆

behavior-based Robot Navigation for Extended Domains

Adaptive behavior 1992年第2期1卷 201-225页

作者： Arkin, Ronald C. Mobile Robot Laboratory College of Computing Georgia Institute of Technology Atlanta GA 30332-0280 United States

behavior-based robotic systems have been successfully deployed for a wide range of planar ground-based tasks. This article describes how reactive (behavior-based) systems can be applied to new and more difficult target domains. ln particular, schema-based navigation is shown to be both feasible and useful in two new areas: three-dimensional navigation for use in aerospace and undersea applications, and “two and one-half”-dimensional surroundings for outdoor navigation in rough terrain. Extensive simulation studies demonstrate the utility of this approach in both cases. © 1992, Sage Publications. All rights reserved.

关键词： behavior-based robotics reactive control robot navigation schema theory

来源：评论

学校读者我要写书评

暂无评论

Extending the potential fields approach to avoid trapping situations

Extending the potential fields approach to avoid trapping si...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Antich, J Ortiz, A Univ Balearic Isl Dept Math & Comp Sci Palma de Mallorca 07122 Spain

ISBN: (纸本)0780389123

Reactive mobile robot navigation based on potential field methods has shown to be a good solution for dealing with unknown and dynamic environments, where timely responses are required. Unfortunately, the complexity of the tasks which can successfully be carried out is restricted by the inherent shortcomings of the approach such as trapping situations due to local minima, difficulties passing among closely spaced obstacles, oscillations in narrow corridors, etc... This paper proposes a novel strategy which overcomes totally the first limitation and partially the others by computing an adaptive navigation function on the basis of such artificial potential fields. As a result, navigation is achieved in very difficult scenarios such as maze-like environments. A comparative study on the path length performance of our proposal with regard to other algorithms from the related literature is also presented. Both simulation and real tests are performed.

关键词： behavior-based robotics reactive navigation artificial potential fields obstacle avoidance

来源：评论

学校读者我要写书评

暂无评论

Flying Animal Inspired behavior-based Gap-Aiming Autonomous Flight with a Small Unmanned Rotorcraft in a Restricted Maneuverability Environment

Flying Animal Inspired Behavior-Based Gap-Aiming Autonomous ...

引用

作者： Sarmiento, Traci Ann Texas A&M University

学位级别：Ph.D.

This dissertation research shows a small unmanned rotorcraft system with onboard processing and a vision sensor can produce autonomous, collision-free flight in a restricted maneuverability environment with no a priori knowledge by using a gap-aiming behavior inspired by flying animals. Current approaches to autonomous flight with small unmanned aerial systems (SUAS) concentrate on detecting and explicitly avoiding obstacles. In contrast, biology indicates that birds, bats, and insects do the opposite; they react to open spaces, or gaps in the environment, with a gap_aiming behavior. Using flying animals as inspiration a behavior-based robotics approach is taken to implement and test their observed gap-aiming behavior in three dimensions. Because biological studies were unclear whether the flying animals were reacting to the largest gap perceived, the closest gap perceived, or all of the gaps three approaches for the perceptual schema were explored in simulation: detect_closest_gap, detect_largest_gap, and detect_all_gaps . The result of these simulations was used in a proof-of-concept implementation on a 3Drobotics Solo quadrotor platform in an environment designed to represent the navigational diffi- culties found inside a restricted maneuverability environment. The motor schema is implemented with an artificial potential field to produce the action of aiming to the center of the gap. Through two sets of field trials totaling fifteen flights conducted with a small unmanned quadrotor, the gap-aiming behavior observed in flying animals is shown to produce repeatable autonomous, collision-free flight in a restricted maneuverability environment. Additionally, using the distance from the starting location to perceived gaps, the horizontal and vertical distance traveled, and the distance from the center of the gap during traversal the implementation of the gap selection approach performs as intended, the three-dimensional movement produced by the motor schema and the ac

关键词： bio-inspired behavior-based robotics small unmanned aerial system disaster robotics Thesis

来源：评论

学校读者我要写书评

暂无评论

Vision-based door-traversal for autonomous mobile robots

Vision-based door-traversal for autonomous mobile robots

引用

IEEE/robotics-Society-of-Japan International Conference on Intelligent Robots and Systems (IROS 2000)

作者： Eberst, C Andersson, M Christensen, HI Tech Univ Munich Inst Real Time Comp Syst D-80333 Munich Germany

ISBN: (纸本)0780363485;0780363493

Robust and safe traversal of doors is an important task for autonomous mobile robots. This paper presents a robust and inexpensive approach for recognizing and localizing doors based on monocular grey-level images and minimalistic models. The traversal is achieved by servoing the robot with respect to the door-hypothesis. Robustness against pose errors, scene complexity, and sensing conditions as obtained by combining indexing on significant aggregated features with a multi-view approach that employs consistency over time: pose-hypotheses are filtered via the motion of the robot to reject incorrect ones. The traversal is implemented as a behavior and was evaluated in 150 experiments cat different doors under different conditions.

关键词： robot vision object recognition pose estimation indexing mobile robots servoing behavior-based robotics

来源：评论

学校读者我要写书评

暂无评论

Online Learning and Teaching of Emergent behaviors in Multi-Robot Teams

引用

IEEE ACCESS 2019年 7卷 158989-159001页

作者： Costa, Luis Feliphe S. do Nascimento, Tiago P. Goncalves, Luiz Marcos G. Univ Fed Rio Grande do Norte UFRN Dept Comp & Automat BR-59064741 Natal RN Brazil Univ Fed Paraiba UFPB Dept Comp Syst Syst Engn & Robot Lab LaSER BR-58051900 Joao Pessoa Paraiba Brazil

In this manuscript, we propose an approach that allows a team of robots to create new (emergent) behaviors at execution time. Basically, we improve the approach called N-Learning used for self-programming of robots in a team, by modifying and extending its functioning structure. The basic capability of behavior sharing is increased by the catching of emergent behaviors at run time. With this, all robots are able not only to share existing knowledge, here represented by blocks of codes containing desired behaviors but also to creating new behaviors as well. Experiments with real robots are presented in order to validate our approach. The experiments demonstrate that after the human-robot interaction with one robot using Program by Demonstration, this robot generates a new behavior at run time and teaches a second robot that performs the same learned behavior through this improved version of the N-learning system.

关键词： Task analysis Multi-robot systems Robot sensing systems Impedance Education Programming Multirobot leaning behavior-based robotics knowledge transference emergent behavior

来源：评论

学校读者我要写书评

暂无评论

Modular behavior-based control for team humanoids

引用

ADVANCED robotics 2004年第7期18卷 659-676页

作者： Lund, HH Pagliarini, L Univ So Denmark Maersk Inst AdapTron Grp DK-5230 Odense M Denmark

When developing teams of humanoids-rather than an individual humanoid-there are a number of issues that become important to consider, including robustness, scalability, versatility, and also development and production costs. Therefore, we used a modern approach to AI that puts emphasis on the balance between control, electronic hardware, material, sensory system and energy in order to develop the team of Viki humanoid robots. In contrast to the top-down approach of equipping a humanoid with as many sensors, motors, power, etc., as possible, we developed a bottom-up approach to the construction of humanoids, regarding both hardware and software (modular behavior-based control). The approach is shown with the development of the Viki humanoid team that won the RoboCup Humanoids Free Style World Championship 2002. In this paper, we focus on the main result of the behavior-based architecture with many layers of behaviors at different levels, which make it easy for both engineers to design new behaviors and for end-users to develop humanoid behaviors at different levels of complexity, dependent on the competencies of the individual end-user. With this architecture, it becomes possible to develop simple user interfaces with a user-guided implementation of our modular behavior-based approach, in order to allow any user to design performances with the humanoid robots.

关键词： humanoids RoboCup behavior-based robotics embodied AI user interaction

来源：评论

学校读者我要写书评

暂无评论

Decision Making for a Mobile Robot Using Potential Function

引用

JOURNAL OF robotics AND MECHATRONICS 2007年第3期19卷 298-307页

作者： Oikawa, Kazumi Takauji, Hidenori Emaru, Takanori Tsuchiya, Takeshi Okubo, Shigenori Yamagata Univ 4-3-16 Jonan Yonezawa Yamagata 9928510 Japan Hokkaido Univ Kita Ku Sapporo Hokkaido 0600814 Japan Hokkaido Univ Kita Ku Sapporo Hokkaido 0608628 Japan Hokkaido Inst Technol Teine Ku Sapporo Hokkaido 0068585 Japan

We discuss decision making for a behavior-based robot with modules which determining robot action. The subsumption architecture (SA) arranges modules in layers, giving upper-layer module action priority over lower-layer modules. Although implementation is easy, results in many inefficient actions because upper-layer module are used regardless of other modules. We solve this problem by representing actions by Potential Function (PF), in which maximum votes are collected from modules. Using event-driven state transition, the robot decides its action with appropriate sets of modules changed based on the situation. We apply this to navigation tasks in a corridor and show simulation results. When we give a map and path designation to the robot, we use a handwriting map interface. We compare object-oriented design SA and PMF with our proposal and show how inefficient actions are reduced using our proposal.

关键词： potential function autonomous mobile robot indoor navigation behavior-based robotics graph map

来源：评论

学校读者我要写书评

暂无评论

On-Orbit Proximity Operations About Controlled Uncooperative Targets Using Meta-Predictor

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2024年第8期47卷 1726-1736页

作者： Fu, Jiangliang Chen, Li Zhang, Dexin Shao, Xiaowei Shanghai Jiao Tong Univ Sch Aeronaut & Astronaut Shanghai Peoples R China Beijing Inst Tracking & Telecommun Technol Beijing 100094 Peoples R China Shanghai Jiao Tong Univ Sch Sensing Sci & Engn Shanghai 200240 Peoples R China

来源：评论

学校读者我要写书评

暂无评论

Incremental robot shaping

引用

CONNECTION SCIENCE 1998年第3-4期10卷 341-360页

作者： Urzelai, J Floreano, D Dorigo, M Colombetti, M Ecole Polytech Fed Lausanne Lab Microcomp CH-1015 Lausanne Switzerland Free Univ Brussels IRIDIA Brussels Belgium Politecn Milan Dipartimento Elettron & Informaz I-20133 Milan Italy

We propose a modular architecture for autonomous robots which allows for the implementation of basic behavioral modules by both programming and training, and accommodates for an evolutionary development of the interconnections among modules. This architecture can implement highly complex controllers and allows for incremental shaping of the robot behavior. Our proposal is exemplified and evaluated experimentally through a number of mobile robotic tasks involving exploration, battery recharging and object manipulation.

关键词： robot shaping incremental evolution behavior-based robotics modular architectures evolution and learning reinforcement learning robot navigation

来源：评论

学校读者我要写书评

暂无评论

behavior arbitration using a fuzzy reinforcement learning approach

引用

INTELLIGENT AUTOMATION AND SOFT COMPUTING 2005年第3期11卷 179-193页

作者： Tehrani, AM Kamel, MS Univ Waterloo Dept Elect & Comp Engn Pattern Anal & Machine Intelligence Lab Waterloo ON N2L 3G1 Canada

Most of the proposed approaches for behavior coordination neglect the issue of learning from experience, which is essential to make an agent capable of adapting to the environment. This subject is mostly addressed by researchers in the area of Reinforcement Learning. In order to investigate the capability of Reinforcement Learning techniques for behavior arbitration, we considered a sub-problem in robotic soccer. We have solved this problem by using Sarsa(lambda) algorithm with a pseudo-fuzzy technique for function approximation. We also compared Sarsa(lambda) with Q(lambda), and CMAC function approximation with the proposed APF technique.

关键词： behavior-based robotics behavior arbitration reinforcement learning SARSA(lambda) pseudo-fuzzy approximator

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：