Fuzzy navigation strategy: application to two distinct autonomous mobile robots

Benreguieg, M.; Hoppenot, Philippe; Maaref, Hichem; Colle, Etienne; Barret, C.

doi:10.1017/s0263574797000738

Cited by 22 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The nonadjusted membership functions requires 625 rules, however the author has not discussed in detail the outcome from the learning method. Benreguieg et al [26] used three inputs which are normalized measured distance on the right, on the left and in front. The normalized inputs with five membership functions reduced the universe of rules to 50 for fuzzy navigation.…”

Section: Generation Of Rule Basementioning

confidence: 99%

A highly interpretable fuzzy rule base using ordinal structure for obstacle avoidance of mobile robot

Samsudin

Ahmad

Mashohor

2011

Applied Soft Computing

View full text Add to dashboard Cite

a b s t r a c tConventional fuzzy logic controller is applicable when there are only two fuzzy inputs with usually one output. Complexity increases when there are more than one inputs and outputs making the system unrealizable. The ordinal structure model of fuzzy reasoning has an advantage of managing high-dimensional problem with multiple input and output variables ensuring the interpretability of the rule set. This is achieved by giving an associated weight to each rule in the defuzzification process. In this work, a methodology to design an ordinal fuzzy logic controller with application for obstacle avoidance of Khepera mobile robot is presented. The implementation will show that ordinal structure fuzzy is easier to design with highly interpretable rules compared to conventional fuzzy controller. In order to achieve high accuracy, a specially tailored Genetic Algorithm (GA) approach for reinforcement learning has been proposed to optimize the ordinal structure fuzzy controller. Simulation results demonstrated improved obstacle avoidance performance in comparison with conventional fuzzy controllers. Comparison of direct and incremental GA for optimization of the controller is also presented.

show abstract

Section: Generation Of Rule Basementioning

confidence: 99%

A highly interpretable fuzzy rule base using ordinal structure for obstacle avoidance of mobile robot

Samsudin

Ahmad

Mashohor

2011

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…Moreover, cost function is interesting to use because we can choose several parameters to optimise the trajectory. All these aspects are detailed in [Hoppenot96] and [Benreguieg97].…”

Section: Trajectory Planningmentioning

confidence: 99%

An Original Approach for a Better Remote Control of an Assistive Robot

Delarue¹,

Nadrag²,

Andriatrimoson³

et al. 2010

Remote and Telerobotics

Self Cite

View full text Add to dashboard Cite

Many researches have been done in the field of assistive robotics in the last few years. The first application field was helping with the disabled people's assistance. Different works have been performed on robotic arms in three kinds of situations. In the first case, static arm, the arm was principally dedicated to office tasks like telephone, fax… Several autonomous modes exist which need to know the precise position of objects. In the second configuration, the arm is mounted on a wheelchair. It follows the person who can employ it in more use cases. But if the person must stay in her/his bed, the arm is no more useful. In a third configuration, the arm is mounted on a separate platform. This configuration allows the largest number of use cases but also poses more difficulties for piloting the robot.The second application field of assistive robotics deals with the assistance at home of people losing their autonomy, for example a person with cognitive impairment. In this case, the assistance deals with two main points: security and cognitive stimulation. In order to ensure the safety of the person at home, different kinds of sensors can be used to detect alarming situations (falls, low cardiac pulse rate…). For assisting a distant operator in alarm detection, the idea is to give him the possibility to have complementary information from a mobile robot about the person's activity at home and to be in contact with the person. Cognitive stimulation is one of the therapeutic means used to maintain as long as possible the maximum of the cognitive capacities of the person. In this case, the robot can be used to bring to the person cognitive stimulation exercises and stimulate the person to perform them.To perform these tasks, it is very difficult to have a totally autonomous robot. In the case of disabled people assistance, it is even not the will of the persons who want to act by themselves. The idea is to develop a semi-autonomous robot that a remote operator can manually pilot with some driving assistances. This is a realistic and somehow desired solution. To achieve that, several scientific problems have to be studied. The first one is human-machine-cooperation. How a remote human operator can control a robot to perform a desired task? One of the key points is to permit the user to understand clearly the way the robot works. Our original approach is to analyse this understanding through appropriation concept introduced by Piaget in 1936. As the robot must have capacities of perception 11 www.intechopen.com Remote and Telerobotics 192decision and action, the second scientific point to address is the robot capacities of autonomy (obstacle avoidance, localisation, path planning…). These two points lead to propose different control modes of the robot by a remote operator, from a totally manual mode to a totally autonomous mode. The most interesting modes are the shared control modes in which the control of the degrees of freedom is shared between the human operator and the robot. The third point is to deal wi...

show abstract

“…For a distant destination, we have implemented an algorithm by which the robot computes a path through the apartment to reach the goal using the known floor plan [16].…”

Section: Human-like Behavior Principlementioning

confidence: 99%

Localization and control of a rehabilitation mobile robot by close human-machine cooperation

Hoppenot

Colle

2001

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

In the field of rehabilitation robotics, a mobile personal robot represents an attractive solution, especially in economic terms in comparison with a desktop workstation. A manipulator arm mounted on a mobile robot can facilitate the restoration of the disabled user's manipulative function. In order both to encourage the person to participate in the task at hand and to be cost effective, close human-machine cooperation is essential. The person controls the robot via a remote station and develops strategies to successfully carry out a mission. The main problems encountered by the person during the execution of a mission are electing to change modes, and the mode transition itself. We have examined two aspects of this cooperation: 1) information exchange between human and machine for decision-making and 2) giving to operators complementary and redundant modes to command the system. An experiment has been conducted to study these two aspects. This paper focuses on the control of robot movements in an indoor environment and especially on localization parameters, human-like robot behavior, and the value of proposing complementary control modes to the operator.

show abstract

Fuzzy navigation strategy: application to two distinct autonomous mobile robots

Cited by 22 publications

References 15 publications

A highly interpretable fuzzy rule base using ordinal structure for obstacle avoidance of mobile robot

A highly interpretable fuzzy rule base using ordinal structure for obstacle avoidance of mobile robot

An Original Approach for a Better Remote Control of an Assistive Robot

Localization and control of a rehabilitation mobile robot by close human-machine cooperation

Contact Info

Product

Resources

About