This paper proposes a new localization strategy for indoor service robots. A mobile robot localization problem is difficult to solve by a single continuous algorithm. Major difficulties include dynamic changes of the real world, various uncertainties, limitation of sensor information, and so forth. To develop a practical localization solution, this paper proposes an integrated localization strategy based on the discrete status of the mobile robot. Uncertainties of navigation are specified and classified into discrete status, and then modeled as a Petri net-based discrete localization system. The proposed algorithm integrates developed computational schemes and robot behaviors with respect to the defined status. Major criteria of status discretization include geometric properties of the environment, existence of dynamic obstacles, and reliability level of the estimated position. An efficient map-matching scheme and a map-building strategy are developed toward practical implementations. This paper focuses on providing a synthesized practical localization method, which can deal with various uncertainties by explicit discretization of robot status. The feasibility of the proposed method is experimentally verified with prototype public service robots in dynamic real environments

Discrete-Status-Based Localization for Indoor Service Robots

We describe a computational cognitive architecture for robots which we call ACT-R/E (ACT-R/Embodied). ACT-R/E is based on ACT-R [1, 2] but uses different visual, auditory, and movement modules. We describe a model that uses ACT-R/E to integrate visual and auditory information to perform conversation tracking in a dynamic environment. We also performed an empirical evaluation study which shows that people see our conversational tracking system as extremely natural.

Integrating vision and audition within a cognitive architecture to track conversations

Robotics researchers have worked hard to realize a long-awaited vision: machines that can eliminate the need for people to work in hazardous environments. Chapter 60 is framed by the vision of disaster response: search and rescue robots carrying people from burning buildings or tunneling through collapsed rock falls to reach trapped miners. In this chapter we review tangible progress towards robots that perform routine work in places too dangerous for humans. Researchers still have many challenges ahead of them but there has been remarkable progress in some areas. Hazardous environments present special challenges for the accomplishment of desired tasks depending on the nature and magnitude of the hazards. Hazards may be present in the form of radiation, toxic contamination, falling objects or potential explosions. Technology that specialized engineering companies can develop and sell without active help from researchers marks the frontier of commercial feasibility. Just inside this border lie teleoperated robots for explosive ordnance disposal (EOD ) and for underwater engineering work. Even with the typical tenfold disadvantage in manipulation performance imposed by the limits of today’s telepresence and teleoperation technology, in terms of human dexterity and speed, robots often can offer a more cost-effective solution. However, most routine applications in hazardous environments still lie far beyond the feasibility frontier. Fire fighting, remediating nuclear contamination, reactor decommissioning, tunneling, underwater engineering, underground mining and clearance of landmines and unexploded ordnance still present many unsolved problems.

Robotics in Hazardous Applications

In this paper, we present the mechatronic design of our Tactile Omnidirectional Robot Manipulator (TOMM), which is a dual arm wheeled humanoid robot with 6DoF on each arm, 4 omnidirectional wheels and 2 switchable end-effectors (1 DoF grippers and 12 DoF Hands). The main feature of TOMM is its arms and hands which are covered with robot skin. We exploit the multi-modal tactile information of our robot skin to provide a rich tactile interaction system for robots. In particular, for the robot TOMM, we provide a general control framework, capable of modifying the dynamic behavior of the entire robot, e.g., producing compliance in a non-compliant system. We present the hardware, software and middleware components of the robot and provide a compendium of the base technologies deployed in it. Furthermore, we show some applications and results that we have obtained using this robot.

TOMM: Tactile omnidirectional mobile manipulator

Mobile robots have been developed for surveillance, reconnaissance and inspection as well as for operation in hazardous environments. Some are intended to explore not only natural terrains but also artificial environments, including stairs. This paper explores algorithms to autonomously climb stairs. The algorithms were derived and implemented for a specific mobile robot with the ability to traverse such obstacles by changing its tracks configuration. Furthermore, algorithms have been developed for conditions under which the mobile robot halts its motion during the climbing process when at risk of flipping over or falling down. The technical problems related to the implementation of some of these functions have been identified and analyzed, and their solutions validated and tested. The algorithms and solutions were validated experimentally, illustrating the effectiveness of autonomous climbing of stairs.

Autonomous Stair Climbing with Reconfigurable Tracked Mobile Robot

This paper presents design and integration of the ROBHAZ-DT3, which is a newly developed mobile robot system with chained double-track mechanisms. A passive adaptation mechanism equipped between the front and rear body enables the ROBHAZ-DT3 to have good adaptability to uneven terrains including stairs. The passive adaptation mechanism reduces energy consumption when moving on uneven terrain as well as its simplicity in design and remote control, since no actuator is necessary for adaptation. Starting from this novel design, dynamic analysis and simulation were conducted to verify the mobility of the double-track mechanism and to obtain significant design parameters such as a suitable track size and an allowable attack angle. Based on this novel mobile platform, a rescue version of the ROBHAZ-DT3 with appropriate sensors and a semi-autonomous mapping and localization algorithm is developed to participate in the RoboCup2004 US-Open: Urban Search and Rescue Competition. From the various experiments in the realistic rescue arena, we can verify that the ROBHAZ-DT3 is reliable in travelling rugged terrain and the proposed mapping and localization algorithm are effective in the unstructured environment with uneven ground.

Rough Terrain Negotiable Mobile Platform with Passively Adaptive Double-Tracks and Its Application to Rescue Missions

This paper presents design and integration of the ROBHAZ-DT3, which is a newly developed mobile robot system with chained double-track mechanisms. It is designed to carry out military and civilian missions in various hazardous environments. A passive adaptation mechanism equipped between the front and rear body enables the ROBHAZ-DT3 to have good adaptability to uneven terrains including stairs. The passive adaptation mechanism reduces energy consumption when moving on uneven terrain as well as its simplicity in design and remote control, since no actuator is necessary for adaptation. Based on this novel mobile platform, a rescue version of the ROBHAZ-DT3 with appropriate sensors and a semi-autonomous mapping and localization algorithm is developed to participate in the RoboCup2004 US-Open: Urban Search and Rescue Competition. From the various experiments in the realistic rescue arena, we can verify that the ROBHAZ-DT3 is reliable in travelling rugged terrain and the proposed mapping and localization algorithm are effective in the unstructured environment with uneven ground.

ROBHAZ-rescue: rough-terrain negotiable teleoperated mobile robot for rescue mission

In this paper, we not only developed a reliable sound localization system including VAD (voice activity detection) component using three microphones but also a face tracking system using a vision camera. Moreover, we proposed a way to integrate these systems in the human-robot interaction to compensate the errors in the localization of a speaker and to reject unnecessary speech or noise signals entering from the undesired directions effectively. For the purpose of verifying our system's performances, we installed the proposed audition and vision system to the prototype robot, called IROBAA (Intelligent ROBot for Active Audition), and showed how to integrate an audio-visual system

Speaker localization among multi-faces in noisy environment by audio-visual integration

This paper proposes a selection framework of multiple navigation primitives for a service robot using Generalized Stochastic Petri Nets (GSPN’s). By adopting probabilistic approach, our framework helps the robot to select the most desirable navigation primitive in run time through the performance estimation according to environmental conditions. Moreover, after a mission, the robot evaluates prior navigation performance from accumulated data, and uses the results for the improvement of future operations. Modeling, analysis, and performance evaluation are conducted on firm mathematical foundation. Also, GSPN’s have several advantages over classic automata or direct use of Markov Process. We conducted simulations of the model derived from our experience of practical installations. The results showed that the framework is useful for primitive selection and performance analysis.

A Selection Framework of Multiple Navigation Primitives Using Generalized Stochastic Petri Nets

This paper proposes a formal selection framework of multiple navigation behaviors for a service robot. In our approach, modeling, analysis, and performance evaluation are carried out based on the generalized stochastic Petri nets (GSPN). By adopting probabilistic approach, our framework helps the robot to select the most desirable navigation behavior in run time according to environmental conditions. Moreover, after a mission, the robot evaluates prior navigation performance from accumulated data, and uses the results for the improvement of future operations. Also, GSPN has several advantages over classic automata or direct use of Markov process. The basic ideas of the framework were introduced in our previous work (Gunhee Kim et al., 2005). Thus, this paper focuses on experimental verification by implementing the framework into the guide robot Jinny. We conduct the experiments about real guidance tasks with visitors in the National Science Museum of Korea. The results show that the proposed strategy is useful to select an appropriate navigation behavior in a dynamic space.

Munsang Kim

Papers

Rough Terrain Negotiable Mobile Platform with Passively Adaptive Double-Tracks and Its Application to Rescue Missions

ROBHAZ-rescue: rough-terrain negotiable teleoperated mobile robot for rescue mission

Speaker localization among multi-faces in noisy environment by audio-visual integration

A Selection Framework of Multiple Navigation Primitives Using Generalized Stochastic Petri Nets

Experimental research of navigation behavior selection using generalized stochastic Petri nets (GSPN) for a tour-guide robot