Constructing a 3-D map of rubble by teleoperated mobile robots with a motion canceling camera system

Yokokohji, Yasuyoshi; Kurisu, M.; Takao, S.; Kudo, Yusuke; Hayashi, Koichiro; Yoshikawa, Tomoki

doi:10.1109/iros.2003.1249636

Cited by 14 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Communication dropouts between the robots are an important concern in these environments, and as a result, maintaining and enhancing connectivity has become a focused research area (Hsieh et al., ; Tardioli et al., ). Furthermore, the difficult task of robots using onboard sensors to map and localize themselves in these unknown and cluttered environments is being addressed through the integration of various simultaneous localization and mapping (SLAM) methods including using an extended information filter algorithm (Ellekilde et al., ), an extended Kalman filter method (Yokokohji et al., ), and a hybrid SLAM approach (Pfingsthorn et al., ). This section focuses on providing a detailed overview of the related work on human‐robot cooperation and multirobot coordination strategies for USAR applications.…”

Section: Related Workmentioning

confidence: 99%

Multirobot Cooperative Learning for Semiautonomous Control in Urban Search and Rescue Applications

Liu

Nejat

2015

Journal of Field Robotics

View full text Add to dashboard Cite

The use of cooperative multirobot teams in urban search and rescue (USAR) environments is a challenging yet promising research area. For multirobot teams working in USAR missions, the objective is to have the rescue robots work effectively together to coordinate task allocation and task execution between different team members in order to minimize the overall exploration time needed to search disaster scenes and to find as many victims as possible. This paper presents the development of a multirobot cooperative learning approach for a hierarchical reinforcement learning (HRL) based semiautonomous control architecture in order to enable a robot team to learn cooperatively to explore and identify victims in cluttered USAR scenes. The proposed cooperative learning approach allows effective task allocation among the multirobot team and efficient execution of the allocated tasks in order to improve the overall team performance. Human intervention is requested by the robots when it is determined that they cannot effectively execute an allocated task autonomously. Thus, the robot team is able to make cooperative decisions regarding task allocation between different team members (robots and human operators) and to share experiences on execution of the allocated tasks. Extensive results verify the effectiveness of the proposed HRL‐based methodology for multi‐robot cooperative exploration and victim identification in USAR‐like scenes.

show abstract

Section: Related Workmentioning

confidence: 99%

Multirobot Cooperative Learning for Semiautonomous Control in Urban Search and Rescue Applications

Liu

Nejat

2015

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…To save victims and to mitigate losses when a disaster occurs, rescue robots have been widely researched throughout the world (1) - (13) . In large-scale disaster sites, professional rescuers are insufficient.…”

Section: Introductionmentioning

confidence: 99%

Volunteers Oriented Interface Design for the Remote Navigation of Tescue Robots at Large-Scale Disaster Sites(To Develop an Efficient Remote Navigation Interface Combined by a Force Feedback Steering Wheel and a Mouse for a Tank Rescue Robot)

Yang

Ito

Saijo

et al. 2005

JSME Int. J., Ser. C

View full text Add to dashboard Cite

This paper aims at constructing an efficient interface being similar to those widely used in human daily life, to fulfill the need of many volunteer rescuers operating rescue robots at large-scale disaster sites. The developed system includes a force feedback steering wheel interface and an artificial neural network (ANN) based mouse-screen interface. The former consists of a force feedback steering control and a six monitors' wall. It provides a manual operation like driving cars to navigate a rescue robot. The latter consists of a mouse and a camera's view displayed in a monitor. It provides a semi-autonomous operation by mouse clicking to navigate a rescue robot. Results of experiments show that a novice volunteer can skillfully navigate a tank rescue robot through both interfaces after 20 to 30 minutes of learning their operation respectively. The steering wheel interface has high navigating speed in open areas, without restriction of terrains and surface conditions of a disaster site. The mouse-screen interface is good at exact navigation in complex structures, while bringing little tension to operators. The two interfaces are designed to switch into each other at any time to provide a combined efficient navigation method.

show abstract

“…In the practical use, the range finder is mounted on the mobile robot whose position cannot be measured directly when the robot is inside rubble. We are investigating a method to estimate the position of robot in the SLAM framework [11]. The method of extracting the environmental features for the SLAM from the picture captured by the NTSC camera is also studied in the research.…”

Section: B Map Building By Online Measurementmentioning

confidence: 99%

“…Experimental results showed that the actual To build a 3D map, the position information of the range finder is needed. We are investigating a method to estimate the position of robot in the SLAM framework [11]. The method of extracting the environmental features for the SLAM from the picture captured by omnivision camera is also studied in our research project of position estimation.…”

Section: Introductionmentioning

confidence: 99%

Development of a laser range finder for 3D map-building in rubble

Kurisu

Yokokohji²,

Oosato³

IEEE International Conference Mechatronics and Automation, 2005

Self Cite

View full text Add to dashboard Cite

In order to search and rescue the victims in rubble effectively, a 3D map of the rubble is required. As a part of the national project of rescue robot system, we are investigating a method for constructing a 3D map of rubble by teleoperated mobile robots. In previous work, we have developed the first prototype of laser range finder for rubble measurement. The developed one consists of a ring laser beam module and an omnivision camera. However, the first prototype has the weakness in which the measurement can be performed only in a dark place, because it is difficult to extract the reflected laser image from the picture captured in a light place. On the contrary, the pictures, in which the contrast of brightness is clarified, are required in order to extract the environmental features which are utilized for the position estimation of the robot based on the SLAM frame work. Also, the texture images captured in a light place are required for constructing virtualized rubble. In this paper, the second prototype of laser range finder which we developed in order to solve above dilemma is described. Although the concept of this prototype is similar to the first one, it has an infrared laser module and two cameras for capturing the reflected laser image and texture image separately. And, a hot mirror is used to dissociate the infrared laser ray from visible rays. We evaluate the measurement accuracy of the second prototype based on the measurement error analysis described in previous work. Using the second laser range finder, 3D maps of rubble were actually built with reasonable accuracy.

show abstract

Constructing a 3-D map of rubble by teleoperated mobile robots with a motion canceling camera system

Cited by 14 publications

References 6 publications

Multirobot Cooperative Learning for Semiautonomous Control in Urban Search and Rescue Applications

Multirobot Cooperative Learning for Semiautonomous Control in Urban Search and Rescue Applications

Volunteers Oriented Interface Design for the Remote Navigation of Tescue Robots at Large-Scale Disaster Sites(To Develop an Efficient Remote Navigation Interface Combined by a Force Feedback Steering Wheel and a Mouse for a Tank Rescue Robot)

Development of a laser range finder for 3D map-building in rubble

Contact Info

Product

Resources

About