1
|
Adiuku N, Avdelidis NP, Tang G, Plastropoulos A. Advancements in Learning-Based Navigation Systems for Robotic Applications in MRO Hangar: Review. Sensors (Basel) 2024; 24:1377. [PMID: 38474913 DOI: 10.3390/s24051377] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/05/2023] [Revised: 02/16/2024] [Accepted: 02/19/2024] [Indexed: 03/14/2024]
Abstract
The field of learning-based navigation for mobile robots is experiencing a surge of interest from research and industry sectors. The application of this technology for visual aircraft inspection tasks within a maintenance, repair, and overhaul (MRO) hangar necessitates efficient perception and obstacle avoidance capabilities to ensure a reliable navigation experience. The present reliance on manual labour, static processes, and outdated technologies limits operation efficiency in the inherently dynamic and increasingly complex nature of the real-world hangar environment. The challenging environment limits the practical application of conventional methods and real-time adaptability to changes. In response to these challenges, recent years research efforts have witnessed advancement with machine learning integration aimed at enhancing navigational capability in both static and dynamic scenarios. However, most of these studies have not been specific to the MRO hangar environment, but related challenges have been addressed, and applicable solutions have been developed. This paper provides a comprehensive review of learning-based strategies with an emphasis on advancements in deep learning, object detection, and the integration of multiple approaches to create hybrid systems. The review delineates the application of learning-based methodologies to real-time navigational tasks, encompassing environment perception, obstacle detection, avoidance, and path planning through the use of vision-based sensors. The concluding section addresses the prevailing challenges and prospective development directions in this domain.
Collapse
Affiliation(s)
- Ndidiamaka Adiuku
- Integrated Vehicle Health Management Centre (IVHM), School of Aerospace, Transport and Manufacturing, Cranfield University, Bedfordshire MK43 0AL, UK
| | - Nicolas P Avdelidis
- Integrated Vehicle Health Management Centre (IVHM), School of Aerospace, Transport and Manufacturing, Cranfield University, Bedfordshire MK43 0AL, UK
| | - Gilbert Tang
- Centre for Robotics and Assembly, School of Aerospace, Transport and Manufacturing (SATM), Cranfield University, Bedfordshire MK43 0AL, UK
| | - Angelos Plastropoulos
- Integrated Vehicle Health Management Centre (IVHM), School of Aerospace, Transport and Manufacturing, Cranfield University, Bedfordshire MK43 0AL, UK
| |
Collapse
|
2
|
Ranjan R, Shin D, Jung Y, Kim S, Yun JH, Kim CH, Lee S, Kye J. Comparative Analysis of Integrated Filtering Methods Using UWB Localization in Indoor Environment. Sensors (Basel) 2024; 24:1052. [PMID: 38400212 PMCID: PMC10892184 DOI: 10.3390/s24041052] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/02/2023] [Revised: 01/30/2024] [Accepted: 01/31/2024] [Indexed: 02/25/2024]
Abstract
This research delves into advancing an ultra-wideband (UWB) localization system through the integration of filtering technologies (moving average (MVG), Kalman filter (KF), extended Kalman filter (EKF)) with a low-pass filter (LPF). We investigated new approaches to enhance the precision and reduce noise of the current filtering methods-MVG, KF, and EKF. Using a TurtleBot robotic platform with a camera, our research thoroughly examines the UWB system in various trajectory situations (square, circular, and free paths with 2 m, 2.2 m, and 5 m distances). Particularly in the square path trajectory with the lowest root mean square error (RMSE) values (40.22 mm on the X axis, and 78.71 mm on the Y axis), the extended Kalman filter with low-pass filter (EKF + LPF) shows notable accuracy. This filter stands out among the others. Furthermore, we find that integrated method using LPF outperforms MVG, KF, and EKF consistently, reducing the mean absolute error (MAE) to 3.39% for square paths, 4.21% for circular paths, and 6.16% for free paths. This study highlights the effectiveness of EKF + LPF for accurate indoor localization for UWB systems.
Collapse
Affiliation(s)
- Rahul Ranjan
- Department of Computer and Electronic Convergence, Intelligent Robot Research Institute, Sun Moon University, Asan 31460, Republic of Korea;
| | - Donggyu Shin
- Department of Computer Engineering, Intelligent Robot Research Institute, Sun Moon University, Asan 31460, Republic of Korea; (D.S.); (Y.J.)
| | - Yoonsik Jung
- Department of Computer Engineering, Intelligent Robot Research Institute, Sun Moon University, Asan 31460, Republic of Korea; (D.S.); (Y.J.)
| | - Sanghyun Kim
- Department of Mechanical Engineering, Kyung Hee University, Suwon 17104, Republic of Korea;
| | - Jong-Hwan Yun
- Mobility Materials-Parts-Equipment Centre, Kongju National University, Kongju 32588, Republic of Korea;
| | - Chang-Hyun Kim
- Department of AI Machinery, Korea Institute of Machinery and Materials, Daejeon 34103, Republic of Korea;
| | - Seungjae Lee
- Department of Computer Engineering, Intelligent Robot Research Institute, Sun Moon University, Asan 31460, Republic of Korea; (D.S.); (Y.J.)
| | - Joongeup Kye
- Department of Mechanical Engineering, Sun Moon University, Asan 31460, Republic of Korea;
| |
Collapse
|
3
|
Bernotat J, Landolfi L, Pasquali D, Nardelli A, Rea F. Remember me - user-centered implementation of working memory architectures on an industrial robot. Front Robot AI 2023; 10:1257690. [PMID: 38116169 PMCID: PMC10728719 DOI: 10.3389/frobt.2023.1257690] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Accepted: 11/16/2023] [Indexed: 12/21/2023] Open
Abstract
The present research is innovative as we followed a user-centered approach to implement and train two working memory architectures on an industrial RB-KAIROS + robot: GRU, a state-of-the-art architecture, and WorkMATe, a biologically-inspired alternative. Although user-centered approaches are essential to create a comfortable and safe HRI, they are still rare in industrial settings. Closing this research gap, we conducted two online user studies with large heterogeneous samples. The major aim of these studies was to evaluate the RB-KAIROS + robot's appearance, movements, and perceived memory functions before (User Study 1) and after the implementation and training of robot working memory (User Study 2). In User Study 1, we furthermore explored participants' ideas about robot memory and what aspects of the robot's movements participants found positive and what aspects they would change. The effects of participants' demographic background and attitudes were controlled for. In User Study 1, participants' overall evaluations of the robot were moderate. Participant age and negative attitudes toward robots led to more negative robot evaluations. According to exploratory analyses, these effects were driven by perceived low experience with robots. Participants expressed clear ideas of robot memory and precise suggestions for a safe, efficient, and comfortable robot navigation which are valuable for further research and development. In User Study 2, the implementation of WorkMATe and GRU led to more positive evaluations of perceived robot memory, but not of robot appearance and movements. Participants' robot evaluations were driven by their positive views of robots. Our results demonstrate that considering potential users' views can greatly contribute to an efficient and positively perceived robot navigation, while users' experience with robots is crucial for a positive HRI.
Collapse
Affiliation(s)
- Jasmin Bernotat
- COgNiTive Architecture for Collaborative Technologies (CONTACT) Unit, Italian Institute of Technology (IIT), Genoa, Italy
| | - Lorenzo Landolfi
- COgNiTive Architecture for Collaborative Technologies (CONTACT) Unit, Italian Institute of Technology (IIT), Genoa, Italy
| | - Dario Pasquali
- COgNiTive Architecture for Collaborative Technologies (CONTACT) Unit, Italian Institute of Technology (IIT), Genoa, Italy
| | - Alice Nardelli
- COgNiTive Architecture for Collaborative Technologies (CONTACT) Unit, Italian Institute of Technology (IIT), Genoa, Italy
- Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), University of Genoa, Genoa, Italy
| | - Francesco Rea
- COgNiTive Architecture for Collaborative Technologies (CONTACT) Unit, Italian Institute of Technology (IIT), Genoa, Italy
| |
Collapse
|
4
|
Ren J, Dai Y, Liu B, Xie P, Wang G. Hierarchical Vision Navigation System for Quadruped Robots with Foothold Adaptation Learning. Sensors (Basel) 2023; 23:s23115194. [PMID: 37299923 DOI: 10.3390/s23115194] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Revised: 05/20/2023] [Accepted: 05/28/2023] [Indexed: 06/12/2023]
Abstract
Legged robots can travel through complex scenes via dynamic foothold adaptation. However, it remains a challenging task to efficiently utilize the dynamics of robots in cluttered environments and to achieve efficient navigation. We present a novel hierarchical vision navigation system combining foothold adaptation policy with locomotion control of the quadruped robots. The high-level policy trains an end-to-end navigation policy, generating an optimal path to approach the target with obstacle avoidance. Meanwhile, the low-level policy trains the foothold adaptation network through auto-annotated supervised learning to adjust the locomotion controller and to provide more feasible foot placement. Extensive experiments in both simulation and the real world show that the system achieves efficient navigation against challenges in dynamic and cluttered environments without prior information.
Collapse
Affiliation(s)
- Junli Ren
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
| | - Yingru Dai
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
| | - Bowen Liu
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
| | - Pengwei Xie
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
| | - Guijin Wang
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
- Shanghai Artificial Intelligence Laboratory, Shanghai 200232, China
| |
Collapse
|
5
|
Zhang Y, Feng Z. Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning. Sensors (Basel) 2023; 23:1810. [PMID: 36850408 PMCID: PMC9961523 DOI: 10.3390/s23041810] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Revised: 01/27/2023] [Accepted: 02/03/2023] [Indexed: 06/18/2023]
Abstract
Efficient navigation in a socially compliant manner is an important and challenging task for robots working in dynamic dense crowd environments. With the development of artificial intelligence, deep reinforcement learning techniques have been widely used in the robot navigation. Previous model-free reinforcement learning methods only considered the interactions between robot and humans, not the interactions between humans and humans. To improve this, we propose a decentralized structured RNN network with coarse-grained local maps (LM-SRNN). It is capable of modeling not only Robot-Human interactions through spatio-temporal graphs, but also Human-Human interactions through coarse-grained local maps. Our model captures current crowd interactions and also records past interactions, which enables robots to plan safer paths. Experimental results show that our model is able to navigate efficiently in dense crowd environments, outperforming state-of-the-art methods.
Collapse
|
6
|
Ferracuti F, Freddi A, Iarlori S, Monteriù A, Omer KIM, Porcaro C. A human-in-the-loop approach for enhancing mobile robot navigation in presence of obstacles not detected by the sensory set. Front Robot AI 2022; 9:909971. [PMID: 36523445 PMCID: PMC9744805 DOI: 10.3389/frobt.2022.909971] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Accepted: 11/07/2022] [Indexed: 04/20/2024] Open
Abstract
Human-in-the-loop approaches can greatly enhance the human-robot interaction by making the user an active part of the control loop, who can provide a feedback to the robot in order to augment its capabilities. Such feedback becomes even more important in all those situations where safety is of utmost concern, such as in assistive robotics. This study aims to realize a human-in-the-loop approach, where the human can provide a feedback to a specific robot, namely, a smart wheelchair, to augment its artificial sensory set, extending and improving its capabilities to detect and avoid obstacles. The feedback is provided by both a keyboard and a brain-computer interface: with this scope, the work has also included a protocol design phase to elicit and evoke human brain event-related potentials. The whole architecture has been validated within a simulated robotic environment, with electroencephalography signals acquired from different test subjects.
Collapse
Affiliation(s)
- Francesco Ferracuti
- Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy
| | - Alessandro Freddi
- Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy
| | - Sabrina Iarlori
- Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy
| | - Andrea Monteriù
- Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy
| | | | - Camillo Porcaro
- Department of Neuroscience and Padova Neuroscience Center (PNC), University of Padova, Padova, Italy
- Institute of Cognitive Sciences and Technologies (ISCT)-National Research Council (CNR), Rome, Italy
- Centre for Human Brain Health, School of Psychology, University of Birmingham, Birmingham, United Kingdom
| |
Collapse
|
7
|
Cheng C, Duan S, He H, Li X, Chen Y. A Generalized Robot Navigation Analysis Platform (RoNAP) with Visual Results Using Multiple Navigation Algorithms. Sensors (Basel) 2022; 22:9036. [PMID: 36501739 PMCID: PMC9737631 DOI: 10.3390/s22239036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/20/2022] [Revised: 11/11/2022] [Accepted: 11/17/2022] [Indexed: 06/17/2023]
Abstract
The robotic navigation task is to find a collision-free path among a mass of stationary or migratory obstacles. Various well-established algorithms have been applied to solve navigation tasks. It is necessary to test the performance of designed navigation algorithms in practice. However, it seems an extremely unwise choice to implement them in a real environment directly unless their performance is guaranteed to be acceptable. Otherwise, it takes time to test navigation algorithms because of a long training process, and imperfect performance may cause damage if the robot collides with obstacles. Hence, it is of key significance to develop a mobile robot analysis platform to simulate the real environment which has the ability to replicate the exact application scenario and be operated in a simple manner. This paper introduces a brand new analysis platform named robot navigation analysis platform (RoNAP), which is an open-source platform developed using the Python environment. A user-friendly interface supports its realization for the evaluation of various navigation algorithms. A variety of existing algorithms were able to achieve desired test results on this platform, indicating its feasibility and efficiency for navigation algorithm analysis.
Collapse
Affiliation(s)
- Chuanxin Cheng
- School of Mechanical and Electrical Engineering, Soochow University, Suzhou 215031, China
| | - Shuang Duan
- School of Mechanical and Electrical Engineering, Soochow University, Suzhou 215031, China
| | - Haidong He
- School of Mechanical and Electrical Engineering, Soochow University, Suzhou 215031, China
| | - Xinlin Li
- Department of Digital Media, Soochow University, Suzhou 215031, China
| | - Yiyang Chen
- School of Mechanical and Electrical Engineering, Soochow University, Suzhou 215031, China
| |
Collapse
|
8
|
Zhang Y, Zhou Y, Li H, Hao H, Chen W, Zhan W. The Navigation System of a Logistics Inspection Robot Based on Multi-Sensor Fusion in a Complex Storage Environment. Sensors (Basel) 2022; 22:s22207794. [PMID: 36298146 PMCID: PMC9611343 DOI: 10.3390/s22207794] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/08/2022] [Revised: 10/07/2022] [Accepted: 10/11/2022] [Indexed: 06/12/2023]
Abstract
To reliably realize the functions of autonomous navigation and cruise of logistics robots in a complex logistics storage environment, this paper proposes a new robot navigation system based on vision and multiline lidar information fusion, which can not only ensure rich information and accurate map edges, but also meet the real-time and accurate positioning and navigation in complex logistics storage scenarios. Simulation and practical verification showed that the robot navigation system is feasible and robust, and overcomes the problems of low precision, poor robustness, weak portability, and difficult expansion of the mobile robot system in a complex environment. It provides a new idea for inspection in an actual logistics storage scenario and has a good prospective application.
Collapse
Affiliation(s)
- Yang Zhang
- College of Economic and Management, Shanghai Polytechnic University, Shanghai 201209, China
| | - Yanjun Zhou
- College of Economic and Management, Shanghai Polytechnic University, Shanghai 201209, China
| | - Hehua Li
- College of Economic and Management, Shanghai Polytechnic University, Shanghai 201209, China
| | - Hao Hao
- College of Economic and Management, Shanghai Polytechnic University, Shanghai 201209, China
| | - Weijiong Chen
- Logistics Research Center, Shanghai Maritime University, Shanghai 201306, China
| | - Weiwei Zhan
- Logistics Research Center, Shanghai Maritime University, Shanghai 201306, China
| |
Collapse
|
9
|
Klančar G, Zdešar A, Krishnan M. Robot Navigation Based on Potential Field and Gradient Obtained by Bilinear Interpolation and a Grid-Based Search. Sensors (Basel) 2022; 22:s22093295. [PMID: 35590987 PMCID: PMC9102480 DOI: 10.3390/s22093295] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/04/2022] [Revised: 04/22/2022] [Accepted: 04/23/2022] [Indexed: 11/16/2022]
Abstract
The original concept of the artificial potential field in robot path planning has spawned a variety of extensions to address its main weakness, namely the formation of local minima in which the robot may be trapped. In this paper, a smooth navigation function combining the Dijkstra-based discrete static potential field evaluation with bilinear interpolation is proposed. The necessary modifications of the bilinear interpolation method are developed to make it applicable to the path-planning application. The effect is that the strategy makes it possible to solve the problem of the local minima, to generate smooth paths with moderate computational complexity, and at the same time, to largely preserve the product of the computationally intensive static plan. To cope with detected changes in the environment, a simple planning strategy is applied, bypassing the static plan with the solution of the A* algorithm to cope with dynamic discoveries. Results from several test environments are presented to illustrate the advantages of the developed navigation model.
Collapse
Affiliation(s)
- Gregor Klančar
- Faculty of Electrical Engineering, University of Ljubljana, Tržaška 25, 1000 Ljubljana, Slovenia; (G.K.); (A.Z.)
| | - Andrej Zdešar
- Faculty of Electrical Engineering, University of Ljubljana, Tržaška 25, 1000 Ljubljana, Slovenia; (G.K.); (A.Z.)
| | - Mohan Krishnan
- Electrical & Computer Engineering and Computer Science Department, University of Detroit Mercy, Detroit, MI 48208, USA
- Correspondence:
| |
Collapse
|
10
|
El-taher FEZ, Taha A, Courtney J, Mckeever S. A Systematic Review of Urban Navigation Systems for Visually Impaired People. Sensors (Basel) 2021; 21:3103. [PMID: 33946857 PMCID: PMC8125253 DOI: 10.3390/s21093103] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Revised: 04/22/2021] [Accepted: 04/25/2021] [Indexed: 11/16/2022]
Abstract
Blind and Visually impaired people (BVIP) face a range of practical difficulties when undertaking outdoor journeys as pedestrians. Over the past decade, a variety of assistive devices have been researched and developed to help BVIP navigate more safely and independently. In addition, research in overlapping domains are addressing the problem of automatic environment interpretation using computer vision and machine learning, particularly deep learning, approaches. Our aim in this article is to present a comprehensive review of research directly in, or relevant to, assistive outdoor navigation for BVIP. We breakdown the navigation area into a series of navigation phases and tasks. We then use this structure for our systematic review of research, analysing articles, methods, datasets and current limitations by task. We also provide an overview of commercial and non-commercial navigation applications targeted at BVIP. Our review contributes to the body of knowledge by providing a comprehensive, structured analysis of work in the domain, including the state of the art, and guidance on future directions. It will support both researchers and other stakeholders in the domain to establish an informed view of research progress.
Collapse
Affiliation(s)
- Fatma El-zahraa El-taher
- School of Computer Science, Technological University Dublin, D07EWV4 Dublin, Ireland; (F.E.-z.E.-t.); (A.T.); (J.C.)
| | - Ayman Taha
- School of Computer Science, Technological University Dublin, D07EWV4 Dublin, Ireland; (F.E.-z.E.-t.); (A.T.); (J.C.)
- Faculty of Computers and Artificial Intelligence, Cairo University, Cairo 12613, Egypt
| | - Jane Courtney
- School of Computer Science, Technological University Dublin, D07EWV4 Dublin, Ireland; (F.E.-z.E.-t.); (A.T.); (J.C.)
| | - Susan Mckeever
- School of Computer Science, Technological University Dublin, D07EWV4 Dublin, Ireland; (F.E.-z.E.-t.); (A.T.); (J.C.)
| |
Collapse
|
11
|
Wu Z, Lu J, Shi T, Zhao X, Zhang X, Yang Y, Wu F, Li Y, Liu Q, Liu M. A Habituation Sensory Nervous System with Memristors. Adv Mater 2020; 32:e2004398. [PMID: 33063391 DOI: 10.1002/adma.202004398] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/29/2020] [Revised: 09/05/2020] [Indexed: 06/11/2023]
Abstract
The sensory nervous system (SNS) builds up the association between external stimuli and the response of organisms. In this system, habituation is a fundamental characteristic that filters out irrelevantly repetitive information and makes the SNS adapt to the external environment. To emulate this critical process in electronic devices, a Lix SiOy -based memristor (TiN/Lix SiOy /Pt) is developed where the temporal response under repetitive stimulation is similar to that of habituation. By connecting this synaptic device to a leaky integrate-and-fire neuron based on a Ag/SiO2 :Ag/Au memristor, a fully memristive SNS with habituation is experimentally demonstrated. Finally, a habituation spiking neural network based on the SNS is built and its application in obstacle avoidance for robot navigation is successfully presented. The results provide that a direct emulation of the biologically inspired learning process by memristors could be a sound choice for neuromorphic hardware implementation.
Collapse
Affiliation(s)
- Zuheng Wu
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Jikai Lu
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- School of Microelectronics, University of Science and Technology of China, Hefei, 230026, China
| | - Tuo Shi
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- Zhejiang Laboratory, Hangzhou, 311122, China
| | - Xiaolong Zhao
- School of Microelectronics, University of Science and Technology of China, Hefei, 230026, China
| | - Xumeng Zhang
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Yang Yang
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Facai Wu
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
| | - Yue Li
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Qi Liu
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Ming Liu
- Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing, 100029, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| |
Collapse
|
12
|
Moreno FA, Monroy J, Ruiz-Sarmiento JR, Galindo C, Gonzalez-Jimenez J. Automatic Waypoint Generation to Improve Robot Navigation Through Narrow Spaces. Sensors (Basel) 2019; 20:E240. [PMID: 31906184 DOI: 10.3390/s20010240] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/26/2019] [Revised: 12/23/2019] [Accepted: 12/29/2019] [Indexed: 11/17/2022]
Abstract
In domestic robotics, passing through narrow areas becomes critical for safe and effective robot navigation. Due to factors like sensor noise or miscalibration, even if the free space is sufficient for the robot to pass through, it may not see enough clearance to navigate, hence limiting its operational space. An approach to facing this is to insert waypoints strategically placed within the problematic areas in the map, which are considered by the robot planner when generating a trajectory and help to successfully traverse them. This is typically carried out by a human operator either by relying on their experience or by trial-and-error. In this paper, we present an automatic procedure to perform this task that: (i) detects problematic areas in the map and (ii) generates a set of auxiliary navigation waypoints from which more suitable trajectories can be generated by the robot planner. Our proposal, fully compatible with the robotic operating system (ROS), has been successfully applied to robots deployed in different houses within the H2020 MoveCare project. Moreover, we have performed extensive simulations with four state-of-the-art robots operating within real maps. The results reveal significant improvements in the number of successful navigations for the evaluated scenarios, demonstrating its efficacy in realistic situations.
Collapse
|
13
|
Ravankar A, Ravankar AA, Rawankar A, Hoshino Y, Kobayashi Y. ITC: Infused Tangential Curves for Smooth 2D and 3D Navigation of Mobile Robots †. Sensors (Basel) 2019; 19:s19204384. [PMID: 31658781 PMCID: PMC6833116 DOI: 10.3390/s19204384] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/27/2019] [Revised: 10/03/2019] [Accepted: 10/07/2019] [Indexed: 11/16/2022]
Abstract
Navigation is an indispensable component of ground and aerial mobile robots. Although there is a plethora of path planning algorithms, most of them generate paths that are not smooth and have angular turns. In many cases, it is not feasible for the robots to execute these sharp turns, and a smooth trajectory is desired. We present 'ITC: Infused Tangential Curves' which can generate smooth trajectories for mobile robots. The main characteristics of the proposed ITC algorithm are: (1) The curves are tangential to the path, thus maintaining G 1 continuity, (2) The curves are infused in the original global path to smooth out the turns, (3) The straight segments of the global path are kept straight and only the sharp turns are smoothed, (4) Safety is embedded in the ITC trajectories and robots are guaranteed to maintain a safe distance from the obstacles, (5) The curvature of ITC curves can easily be controlled and smooth trajectories can be generated in real-time, (6) The ITC algorithm smooths the global path on a part-by-part basis thus local smoothing at one point does not affect the global path. We compare the proposed ITC algorithm with traditional interpolation based trajectory smoothing algorithms. Results show that, in case of mobile navigation in narrow corridors, ITC paths maintain a safe distance from both walls, and are easy to generate in real-time. We test the algorithm in complex scenarios to generate curves of different curvatures, while maintaining different safety thresholds from obstacles in vicinity. We mathematically discuss smooth trajectory generation for both 2D navigation of ground robots, and 3D navigation of aerial robots. We also test the algorithm in real environments with actual robots in a complex scenario of multi-robot collision avoidance. Results show that the ITC algorithm can be generated quickly and is suitable for real-world scenarios of collision avoidance in narrow corridors.
Collapse
Affiliation(s)
- Abhijeet Ravankar
- School of Regional Innovation and Social Design Engineering, Faculty of Engineering, Kitami Institute of Technology, Kitami, Hokkaido 090-8507, Japan.
| | - Ankit A Ravankar
- Division of Human Mechanical Systems and Design, Faculty of Engg., Hokkaido University, Sapporo, Hokkaido 060-8628, Japan.
| | - Arpit Rawankar
- Department of Electronics and Telecommunication, Vidyalankar Institute of Technology, Mumbai 400037, India.
| | - Yohei Hoshino
- School of Regional Innovation and Social Design Engineering, Faculty of Engineering, Kitami Institute of Technology, Kitami, Hokkaido 090-8507, Japan.
| | - Yukinori Kobayashi
- Division of Human Mechanical Systems and Design, Faculty of Engg., Hokkaido University, Sapporo, Hokkaido 060-8628, Japan.
| |
Collapse
|
14
|
Zhou X, Gao Y, Guan L. Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners. Sensors (Basel) 2019; 19:E176. [PMID: 30621314 PMCID: PMC6339171 DOI: 10.3390/s19010176] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/13/2018] [Revised: 12/13/2018] [Accepted: 12/25/2018] [Indexed: 11/23/2022]
Abstract
Robot navigation is a fundamental problem in robotics and various approaches have been developed to cope with this problem. Despite the great success of previous approaches, learning-based methods are receiving growing interest in the research community. They have shown great efficiency in solving navigation tasks and offer considerable promise to build intelligent navigation systems. This paper presents a goal-directed robot navigation system that integrates global planning based on goal-directed end-to-end learning and local planning based on reinforcement learning (RL). The proposed system aims to navigate the robot to desired goal positions while also being adaptive to changes in the environment. The global planner is trained to imitate an expert's navigation between different positions by goal-directed end-to-end learning, where both the goal representations and local observations are incorporated to generate actions. However, it is trained in a supervised fashion and is weak in dealing with changes in the environment. To solve this problem, a local planner based on deep reinforcement learning (DRL) is designed. The local planner is first implemented in a simulator and then transferred to the real world. It works complementarily to deal with situations that have not been met during training the global planner and is able to generalize over different situations. The experimental results on a robot platform demonstrate the effectiveness of the proposed navigation system.
Collapse
Affiliation(s)
- Xiaomao Zhou
- College of Automation, Harbin Engineering University, Harbin 150001, China.
| | - Yanbin Gao
- College of Automation, Harbin Engineering University, Harbin 150001, China.
| | - Lianwu Guan
- College of Automation, Harbin Engineering University, Harbin 150001, China.
| |
Collapse
|
15
|
Shao Z, Wu P, Zhu E, Chen L. On Metric Dimension in Some Hex Derived Networks. Sensors (Basel) 2018; 19:s19010094. [PMID: 30597887 PMCID: PMC6338904 DOI: 10.3390/s19010094] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/29/2018] [Revised: 12/18/2018] [Accepted: 12/26/2018] [Indexed: 11/28/2022]
Abstract
The concept of a metric dimension was proposed to model robot navigation where the places of navigating agents can change among nodes. The metric dimension md(G) of a graph G is the smallest number k for which G contains a vertex set W, such that |W|=k and every pair of vertices of G possess different distances to at least one vertex in W. In this paper, we demonstrate that md(HDN1(n))=4 for n≥2. This indicates that in these types of hex derived sensor networks, the least number of nodes needed for locating any other node is four.
Collapse
Affiliation(s)
- Zehui Shao
- Institute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, China.
| | - Pu Wu
- Institute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, China.
| | - Enqiang Zhu
- Institute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, China.
| | - Lanxiang Chen
- College of Mathematics and Informatics, Fujian Normal University, Fujian Provincial Key Laboratory of Network Security and Cryptology, Fujian Network & Information Security Industry Technology Development Base, Fuzhou 350117, China.
| |
Collapse
|
16
|
Ravankar A, Ravankar AA, Kobayashi Y, Hoshino Y, Peng CC. Path Smoothing Techniques in Robot Navigation: State-of-the-Art, Current and Future Challenges. Sensors (Basel) 2018; 18:E3170. [PMID: 30235894 DOI: 10.3390/s18093170] [Citation(s) in RCA: 116] [Impact Index Per Article: 19.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/08/2018] [Revised: 09/14/2018] [Accepted: 09/17/2018] [Indexed: 11/28/2022]
Abstract
Robot navigation is an indispensable component of any mobile service robot. Many path planning algorithms generate a path which has many sharp or angular turns. Such paths are not fit for mobile robot as it has to slow down at these sharp turns. These robots could be carrying delicate, dangerous, or precious items and executing these sharp turns may not be feasible kinematically. On the contrary, smooth trajectories are often desired for robot motion and must be generated while considering the static and dynamic obstacles and other constraints like feasible curvature, robot and lane dimensions, and speed. The aim of this paper is to succinctly summarize and review the path smoothing techniques in robot navigation and discuss the challenges and future trends. Both autonomous mobile robots and autonomous vehicles (outdoor robots or self-driving cars) are discussed. The state-of-the-art algorithms are broadly classified into different categories and each approach is introduced briefly with necessary background, merits, and drawbacks. Finally, the paper discusses the current and future challenges in optimal trajectory generation and smoothing research.
Collapse
|
17
|
Albrektsen SM, Johansen TA. User-Configurable Timing and Navigation for UAVs. Sensors (Basel) 2018; 18:s18082468. [PMID: 30061522 PMCID: PMC6111879 DOI: 10.3390/s18082468] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/25/2018] [Revised: 07/20/2018] [Accepted: 07/24/2018] [Indexed: 11/16/2022]
Abstract
As the use of unmanned aerial vehicles (UAVs) for industrial use increases, so are the demands for highly accurate navigation solutions, and with the high dynamics that UAVs offer, the accuracy of a measurement does not only depend on the value of the measurement, but also the accuracy of the associated timestamp. Sensor timing using dedicated hardware is the de-facto method to achieve optimal sensor performance, but the solutions available today have limited flexibility and requires much effort when changing sensors. This article presents requirements and suggestions for a highly accurate, reconfigurable sensor timing system that simplifies integration of sensor systems and navigation systems for UAVs. Both typical avionics sensors, like GNSS receivers and IMUs, and more complex sensors, such as cameras, are supported. To verify the design, an implementation named the SenTiBoard was created, along with a software support package and a baseline sensor-suite. With the solution presented in this paper we get a measurement resolution of 10 nanoseconds and we can transfer up to 7.6 megabytes per second. If the sensor suite includes a GNSS receiver with a pulse-per-second (PPS) reference, the sensor measurements can be related to an absolute time reference (UTC) with a clock drift of 1.9 microseconds per second RMS. An experiment was carried out, using a Mini Cruiser fixed-wing UAV, where errors in georeferencing infrared images were reduced with a factor of 4 when compared to a software synchronization method.
Collapse
Affiliation(s)
- Sigurd M Albrektsen
- Department of Engineering Cybernetics, Centre for Autonomous Marine Operations and Systems, Norwegian University of Science and Technology (NTNU-AMOS), O.S. Bragstads plass 2D, 7034 Trondheim, Norway.
| | - Tor Arne Johansen
- Department of Engineering Cybernetics, Centre for Autonomous Marine Operations and Systems, Norwegian University of Science and Technology (NTNU-AMOS), O.S. Bragstads plass 2D, 7034 Trondheim, Norway.
| |
Collapse
|
18
|
Socas R, Dormido R, Dormido S. New Control Paradigms for Resources Saving: An Approach for Mobile Robots Navigation. Sensors (Basel) 2018; 18:E281. [PMID: 29346321 DOI: 10.3390/s18010281] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/16/2017] [Revised: 01/08/2018] [Accepted: 01/11/2018] [Indexed: 11/23/2022]
Abstract
In this work, an event-based control scheme is presented. The proposed system has been developed to solve control problems appearing in the field of Networked Control Systems (NCS). Several models and methodologies have been proposed to measure different resources consumptions. The use of bandwidth, computational load and energy resources have been investigated. This analysis shows how the parameters of the system impacts on the resources efficiency. Moreover, the proposed system has been compared with its equivalent discrete-time solution. In the experiments, an application of NCS for mobile robots navigation has been set up and its resource usage efficiency has been analysed.
Collapse
|
19
|
Hernández AC, Gómez C, Crespo J, Barber R. Object Detection Applied to Indoor Environments for Mobile Robot Navigation. Sensors (Basel) 2016; 16:E1180. [PMID: 27483264 DOI: 10.3390/s16081180] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/06/2016] [Revised: 06/28/2016] [Accepted: 07/20/2016] [Indexed: 11/19/2022]
Abstract
To move around the environment, human beings depend on sight more than their other senses, because it provides information about the size, shape, color and position of an object. The increasing interest in building autonomous mobile systems makes the detection and recognition of objects in indoor environments a very important and challenging task. In this work, a vision system to detect objects considering usual human environments, able to work on a real mobile robot, is developed. In the proposed system, the classification method used is Support Vector Machine (SVM) and as input to this system, RGB and depth images are used. Different segmentation techniques have been applied to each kind of object. Similarly, two alternatives to extract features of the objects are explored, based on geometric shape descriptors and bag of words. The experimental results have demonstrated the usefulness of the system for the detection and location of the objects in indoor environments. Furthermore, through the comparison of two proposed methods for extracting features, it has been determined which alternative offers better performance. The final results have been obtained taking into account the proposed problem and that the environment has not been changed, that is to say, the environment has not been altered to perform the tests.
Collapse
|
20
|
Lu K, Li J, An X, He H. Vision Sensor-Based Road Detection for Field Robot Navigation. Sensors (Basel) 2015; 15:29594-617. [PMID: 26610514 DOI: 10.3390/s151129594] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/21/2015] [Revised: 11/13/2015] [Accepted: 11/17/2015] [Indexed: 11/29/2022]
Abstract
Road detection is an essential component of field robot navigation systems. Vision sensors play an important role in road detection for their great potential in environmental perception. In this paper, we propose a hierarchical vision sensor-based method for robust road detection in challenging road scenes. More specifically, for a given road image captured by an on-board vision sensor, we introduce a multiple population genetic algorithm (MPGA)-based approach for efficient road vanishing point detection. Superpixel-level seeds are then selected in an unsupervised way using a clustering strategy. Then, according to the GrowCut framework, the seeds proliferate and iteratively try to occupy their neighbors. After convergence, the initial road segment is obtained. Finally, in order to achieve a globally-consistent road segment, the initial road segment is refined using the conditional random field (CRF) framework, which integrates high-level information into road detection. We perform several experiments to evaluate the common performance, scale sensitivity and noise sensitivity of the proposed method. The experimental results demonstrate that the proposed method exhibits high robustness compared to the state of the art.
Collapse
|
21
|
Zhu Q, Liu C, Cai C. A novel robot visual homing method based on SIFT features. Sensors (Basel) 2015; 15:26063-84. [PMID: 26473880 DOI: 10.3390/s151026063] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/02/2015] [Revised: 09/30/2015] [Accepted: 10/09/2015] [Indexed: 11/18/2022]
Abstract
Warping is an effective visual homing method for robot local navigation. However, the performance of the warping method can be greatly influenced by the changes of the environment in a real scene, thus resulting in lower accuracy. In order to solve the above problem and to get higher homing precision, a novel robot visual homing algorithm is proposed by combining SIFT (scale-invariant feature transform) features with the warping method. The algorithm is novel in using SIFT features as landmarks instead of the pixels in the horizon region of the panoramic image. In addition, to further improve the matching accuracy of landmarks in the homing algorithm, a novel mismatching elimination algorithm, based on the distribution characteristics of landmarks in the catadioptric panoramic image, is proposed. Experiments on image databases and on a real scene confirm the effectiveness of the proposed method.
Collapse
|
22
|
Abstract
Mobile robots and animals alike must effectively navigate their environments in order to achieve their goals. For animals goal-directed navigation facilitates finding food, seeking shelter or migration; similarly robots perform goal-directed navigation to find a charging station, get out of the rain or guide a person to a destination. This similarity in tasks extends to the environment as well; increasingly, mobile robots are operating in the same underwater, ground and aerial environments that animals do. Yet despite these similarities, goal-directed navigation research in robotics and biology has proceeded largely in parallel, linked only by a small amount of interdisciplinary research spanning both areas. Most state-of-the-art robotic navigation systems employ a range of sensors, world representations and navigation algorithms that seem far removed from what we know of how animals navigate; their navigation systems are shaped by key principles of navigation in 'real-world' environments including dealing with uncertainty in sensing, landmark observation and world modelling. By contrast, biomimetic animal navigation models produce plausible animal navigation behaviour in a range of laboratory experimental navigation paradigms, typically without addressing many of these robotic navigation principles. In this paper, we attempt to link robotics and biology by reviewing the current state of the art in conventional and biomimetic goal-directed navigation models, focusing on the key principles of goal-oriented robotic navigation and the extent to which these principles have been adapted by biomimetic navigation models and why.
Collapse
Affiliation(s)
- Michael Milford
- School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland 4000, Australia
| | - Ruth Schulz
- School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland 4000, Australia
| |
Collapse
|
23
|
Abstract
As a fundamental research topic, autonomous indoor robot navigation continues to be a challenge in unconstrained real-world indoor environments. Although many models for map-building and planning exist, it is difficult to integrate them due to the high amount of noise, dynamics, and complexity. Addressing this challenge, this paper describes a neural model for environment mapping and robot navigation based on learning spatial knowledge. Considering that a person typically moves within a room without colliding with objects, this model learns the spatial knowledge by observing the person's movement using a ceiling-mounted camera. A robot can plan and navigate to any given position in the room based on the acquired map, and adapt it based on having identified possible obstacles. In addition, salient visual features are learned and stored in the map during navigation. This anchoring of visual features in the map enables the robot to find and navigate to a target object by showing an image of it. We implement this model on a humanoid robot and tests are conducted in a home-like environment. Results of our experiments show that the learned sensorimotor map masters complex navigation tasks.
Collapse
Affiliation(s)
- Wenjie Yan
- Knowledge Technology Group, Department of Computer Science, University of Hamburg Hamburg, Germany
| | | | | |
Collapse
|
24
|
Kinjo K, Uchibe E, Doya K. Evaluation of linearly solvable Markov decision process with dynamic model learning in a mobile robot navigation task. Front Neurorobot 2013; 7:7. [PMID: 23576983 PMCID: PMC3617398 DOI: 10.3389/fnbot.2013.00007] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2012] [Accepted: 03/15/2013] [Indexed: 11/13/2022] Open
Abstract
Linearly solvable Markov Decision Process (LMDP) is a class of optimal control problem in which the Bellman's equation can be converted into a linear equation by an exponential transformation of the state value function (Todorov, 2009b). In an LMDP, the optimal value function and the corresponding control policy are obtained by solving an eigenvalue problem in a discrete state space or an eigenfunction problem in a continuous state using the knowledge of the system dynamics and the action, state, and terminal cost functions. In this study, we evaluate the effectiveness of the LMDP framework in real robot control, in which the dynamics of the body and the environment have to be learned from experience. We first perform a simulation study of a pole swing-up task to evaluate the effect of the accuracy of the learned dynamics model on the derived the action policy. The result shows that a crude linear approximation of the non-linear dynamics can still allow solution of the task, despite with a higher total cost. We then perform real robot experiments of a battery-catching task using our Spring Dog mobile robot platform. The state is given by the position and the size of a battery in its camera view and two neck joint angles. The action is the velocities of two wheels, while the neck joints were controlled by a visual servo controller. We test linear and bilinear dynamic models in tasks with quadratic and Guassian state cost functions. In the quadratic cost task, the LMDP controller derived from a learned linear dynamics model performed equivalently with the optimal linear quadratic regulator (LQR). In the non-quadratic task, the LMDP controller with a linear dynamics model showed the best performance. The results demonstrate the usefulness of the LMDP framework in real robot control even when simple linear models are used for dynamics learning.
Collapse
Affiliation(s)
- Ken Kinjo
- Neural Computation Laboratory, Graduate School of Information Science, Nara Institute of Science and Technology Ikoma, Nara, Japan ; Neural Computation Unit, Okinawa Institute of Science and Technology Onna-son, Okinawa, Japan
| | | | | |
Collapse
|
25
|
Elfwing S, Uchibe E, Doya K. Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces. Front Neurorobot 2013; 7:3. [PMID: 23450126 PMCID: PMC3584292 DOI: 10.3389/fnbot.2013.00003] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2012] [Accepted: 02/12/2013] [Indexed: 11/17/2022] Open
Abstract
Free-energy based reinforcement learning (FERL) was proposed for learning in high-dimensional state- and action spaces, which cannot be handled by standard function approximation methods. In this study, we propose a scaled version of free-energy based reinforcement learning to achieve more robust and more efficient learning performance. The action-value function is approximated by the negative free-energy of a restricted Boltzmann machine, divided by a constant scaling factor that is related to the size of the Boltzmann machine (the square root of the number of state nodes in this study). Our first task is a digit floor gridworld task, where the states are represented by images of handwritten digits from the MNIST data set. The purpose of the task is to investigate the proposed method's ability, through the extraction of task-relevant features in the hidden layer, to cluster images of the same digit and to cluster images of different digits that corresponds to states with the same optimal action. We also test the method's robustness with respect to different exploration schedules, i.e., different settings of the initial temperature and the temperature discount rate in softmax action selection. Our second task is a robot visual navigation task, where the robot can learn its position by the different colors of the lower part of four landmarks and it can infer the correct corner goal area by the color of the upper part of the landmarks. The state space consists of binarized camera images with, at most, nine different colors, which is equal to 6642 binary states. For both tasks, the learning performance is compared with standard FERL and with function approximation where the action-value function is approximated by a two-layered feedforward neural network.
Collapse
Affiliation(s)
- Stefan Elfwing
- Neural Computation Unit, Okinawa Institute of Science and Technology, Graduate University Okinawa, Japan
| | | | | |
Collapse
|
26
|
Sergiyenko O, Hernandez W, Tyrsa V, Cruz LF, Starostenko O, Peña-Cabrera M. Remote sensor for spatial measurements by using optical scanning. Sensors (Basel) 2009; 9:5477-92. [PMID: 22346709 DOI: 10.3390/s90705477] [Citation(s) in RCA: 25] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/21/2009] [Revised: 07/08/2009] [Accepted: 07/10/2009] [Indexed: 11/17/2022]
Abstract
In this paper, we propose a low-cost contact-free measurement system for both 3-D data acquisition and fast surface parameter registration by digitized points. Despite the fact that during the last decade several approaches for both contact-free measurement techniques aimed at carrying out object surface recognition and 3-D object recognition have been proposed, they often still require complex and expensive equipment. Therefore, alternative low cost solutions are in great demand. Here, two low-cost solutions to the above-mentioned problem are presented. These are two examples of practical applications of the novel passive optical scanning system presented in this paper.
Collapse
|
27
|
Chen W, Mei T, Meng MQH, Liang H, Liu Y, Li Y, Li S. Localization Algorithm Based on a Spring Model (LASM) for Large Scale Wireless Sensor Networks. Sensors (Basel) 2008; 8:1797-1818. [PMID: 27879793 PMCID: PMC3663024 DOI: 10.3390/s8031797] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/06/2007] [Accepted: 03/12/2008] [Indexed: 11/16/2022]
Abstract
A navigation method for a lunar rover based on large scale wireless sensor networks is proposed. To obtain high navigation accuracy and large exploration area, high node localization accuracy and large network scale are required. However, the computational and communication complexity and time consumption are greatly increased with the increase of the network scales. A localization algorithm based on a spring model (LASM) method is proposed to reduce the computational complexity, while maintaining the localization accuracy in large scale sensor networks. The algorithm simulates the dynamics of physical spring system to estimate the positions of nodes. The sensor nodes are set as particles with masses and connected with neighbor nodes by virtual springs. The virtual springs will force the particles move to the original positions, the node positions correspondingly, from the randomly set positions. Therefore, a blind node position can be determined from the LASM algorithm by calculating the related forces with the neighbor nodes. The computational and communication complexity are O(1) for each node, since the number of the neighbor nodes does not increase proportionally with the network scale size. Three patches are proposed to avoid local optimization, kick out bad nodes and deal with node variation. Simulation results show that the computational and communication complexity are almost constant despite of the increase of the network scale size. The time consumption has also been proven to remain almost constant since the calculation steps are almost unrelated with the network scale size.
Collapse
Affiliation(s)
- Wanming Chen
- Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, 230031, P. R. China; E-mail:
- Department of Automation, University of Science and Technology of China, Hefei, 230027, P.R. China
| | - Tao Mei
- Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, 230031, P. R. China; E-mail:
- Author to whom correspondence should be addressed; E-mail:
| | - Max Q.-H. Meng
- Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, 230031, P. R. China; E-mail:
- Department of Electronic Engineering, The Chinese University of Hong Kong, Sha Tian, Hong Kong; E-mail:
| | - Huawei Liang
- Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, 230031, P. R. China; E-mail:
| | - Yumei Liu
- Department of Automation, University of Science and Technology of China, Hefei, 230027, P.R. China
| | - Yangming Li
- Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, 230031, P. R. China; E-mail:
- Department of Automation, University of Science and Technology of China, Hefei, 230027, P.R. China
| | - Shuai Li
- Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, 230031, P. R. China; E-mail:
- Department of Automation, University of Science and Technology of China, Hefei, 230027, P.R. China
| |
Collapse
|