Robot box-pushing with environment-embedded sensors

Verma, Amar S.; Jung, Boyoon; Sukhatme, Gaurav S.

doi:10.1109/cira.2001.1013199

Cited by 8 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detrimental effect of Rayleigh noise is the most prominent one, while all the algorithms have performed satisfactorily in the presence of Gaussian noise. However, the results given in Table-I indicate that the performance of the proposed ENNSBC remains consistently better than its competitor algorithms with respect to the energy, the time, and the number of steps required to complete the task for a particular value of 2 , irrespective of noise distribution. The simulations results for these experiments in three arenas in the presence of noise following Gaussian, Poisson, and Rayleigh distribution (with specific variance) are respectively given in Fig.…”

Section: (A) Experiments In Simulated Environmentmentioning

confidence: 91%

“…represents the normalized estimate of J k,i * (0, 1) for k= [1,2]. The effective non-dominated food source i Y A having the lowest J i for i= [1, |A|] is now identified for decoding the optimal solution (food source) for the single step local movement of the box as obtained by ENNSBC.…”

Section: (A) Experiments In Simulated Environmentmentioning

confidence: 99%

“…The population P(G) is then sorted into a number of Pareto fronts (FS(1), FS (2), FS (3), and so on) according to nondomination [12]. After that, a slightly inferior food source ( )…”

Section: F Non-dominated Sorting and Pareto Co-rankingmentioning

confidence: 99%

See 2 more Smart Citations

Multi-robot box-pushing in presence of measurement noise

Rakshit

Konar

Nagar

2016

2016 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Abstract-Real-world multi-robot co-ordination problems, involving system (robot) design, control, and planning are often formulated in the settings of an optimization problem with a view to maximize system throughput/efficiency under the constraints on system resources. The paper aims at solving a multi-robot box-pushing problem in the presence of noisy sensory data using evolutionary algorithm. The process of co-ordination among multiple robots is characterized by a set of measurements and a set of estimators with a mathematical relationship between them (captured by the objective function). In the box-pushing problem by twin robots, the range data obtained by the robots at any instant of time are measurements, and the torque and/or force to be developed by the robots for a local movement of the box are estimators. We here use torques and forces developed by the robots to construct two objectives on minimization of energy consumed and time required for a local movement of the box in the presence of noisy sensory data. The box-pushing problem is solved using the proposed extended noisy non-dominated sorting bee colony (ENNSBC) algorithm to handle noise in the objective surfaces. Experiments undertaken in both simulation and realworld platforms reveal the superiority of the proposed ENNSBC to other competitor algorithms to solve the box-pushing problem with respect to the performance metrics defined in the literature.

show abstract

Section: (A) Experiments In Simulated Environmentmentioning

confidence: 91%

Section: (A) Experiments In Simulated Environmentmentioning

confidence: 99%

See 1 more Smart Citation

Multi-robot box-pushing in presence of measurement noise

Rakshit

Konar

Nagar

2016

2016 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

show abstract

“…Their method replaces the boolean membership with graded membership to obtain a continuous control surface over the input variables. Verma et al [117] described an approach using off-board, environment embedded sensor network to help the pusher robot in detecting and pushing objects. However, this method imposes a restriction that a large environment requires a large number of environment-embedded sensors, which further leads to the problem of efficient sensor selection and sensor fusion.…”

Section: Introductionmentioning

confidence: 99%

Behavior-based Robot Control Using Fuzzy Discrete Event System

Huq

Mann

Gosine

2006

2006 IEEE International Conference on Fuzzy Systems

View full text Add to dashboard Cite

The key issue associated with behavior-based architecture is the development of a behavior coordinator. A behavior coordinator should possess a number of important properties. The literature suggests that (a) both behavior arbitration and command fusion techniques should be combined in order to coordinate competitive and cooperative behaviors, (b) the coordinator should possess adequate means of modeling the current state of the world, (c) sensory uncertainties should be modeled using multivalued logic, (d) the coordinator should be capable of making persistent behavior selection, (e) it should provide the opportunity to accommodate hierarchical decisionmaking for reactive action generation, (f) it should possess predictive decision-making capability for handling future environmental uncertainties, (g) it should provide satisfactory means of decision analysis, and finally (h) it should be modular to achieve robustness with a larger number of behaviors. This thesis attempts to address some of the issues mentioned above while exploiting fuzzy logic (FL) based methodologies for behavior coordination.The initial investigation includes experimentation of different methodologies in the literature. A FL-based controller is designed for motor schema based mobile robot navigation. Fuzzy meta rules have been used to adaptively generate weights for each motor schema. It uses human reasoning to model the deterministic uncertainty of sensory data, which in turn helps to reduce the possibility of generating incorrect weights for motor schemas. Experimental results demonstrate that the fuzzy logic based approach overcomes some of the common problems of schema-based navigation.It has been observed that a pure FL-based method has several disadvantages, such as it imposes a scalability problem when the system consists of both competitive and cooperative behaviors and it does not provide any feedback measures for decision analysis. Moreover, the rule-based knowledge representation becomes complex in cases where previous state information is incorporated for persistent decision-making.While understanding the shortcomings of each technique, this thesis present a novel behavior coordination architecture using Fuzzy Discrete Event System (FDES).This architecture addresses the shortcomings of the FL-based technique using complimentary properties of Discrete Event System (DES). The DES-based method provides supervisory control techniques for behavior arbitration and has a suitable framework for decision analysis in terms of observability and controllability. Furthermore, it supports multi-level behavioral decomposition and uses previous state information of the system for persistent decision-making. As a result, the combination of FL and DES provides the opportunity to integrate several key features to achieve a high performance behavior coordinator.Finally the proposed architecture is experimentally tested using three different robotic applications, namely robotic navigation, robotic box pulling and robotic visual attention. Th...

show abstract

“…In which, multi sensor is often used to assure the object being pushed as desired (1) (3)- (6) . Verma (3) performs box-pushing by a simple mobile robot with environment-embedded sensors. The robot pushes a detected object based on pose information obtained * Keio University Dept.…”

Section: Introductionmentioning

confidence: 99%

Soft Pushing Operation with Dual Compliance Controllers Based on Estimated Torque and Visual Force

Muis

Ohnishi

2007

IEEJ Trans. IA

View full text Add to dashboard Cite

Future robot is expected to accomplish more and more complex task, especially to work with human life. Indeed, the robot should be compliance with environment either human being. An interesting application in such an issue is pushing operation.Generally, the pushing operation consists of "approaching, touching, and pushing". However, most researches in this field are dealing with how the pushed object follows the object's trajectory. Obviously, one needs to considers the damage that may happened to the object during "touching" stage, especially if pushing operation is done by robot with high momentum.Indeed, this paper proposes a novel structure for soft pushing operation with dual compliance controllers. The robot motion will be controlled in three stages of pushing operation; approaching, touching and pushing. Although a compliance control provides robot with affinity and adaptability to work in open environment, a compliance control while touching is not enough for robot with high momentum. In which, the robot should slow down while approaching the object. Fig. 1 shows the pushing operation without any compliance behavior. Although the position response tightly followed the position command, the robot does not care whether it hit any damage on the object. The robot treats the object as an obstacle to be vanished as long it follows the position command.The compliance controller in this paper is not only for touching stage, but also for the whole stages; approaching, touching and pushing. Generally, compliance control is a control system with trajectory compensation so that an external force may be followed. The first compliance controller in this paper is driven by estimated external force based on reaction torque observer. This controller is Fig. 1. Pushing operation without any compliance behavior projected to compensate contact sensation. The second controller compensates non-contact sensation. Surely, a force sensation from force sensor either reaction torque observer is available just after the robot touched the object. It is too risky to damage the object while touching. Indeed, a visual sensor is considered as non-contact sensation. Instead of using visual information as command reference, the visual information such as depth in this paper, is treated as visual force for the second compliance controller.A heavy mobile manipulator and heavy object are considered in this paper. A chopstick is attached on the object side to show the effectiveness of the proposed method. In overall, both compliance controllers adjust the mobile manipulator command reference to provide soft pushing operation.Based on experimental results, dual compliance controllers is not enough. Although the soft pushing operation is realized, the position response could not follow the position command. Indeed, a modification on compliance controller reference is applied. The objective of this modification is to make sure the robot still follow the position command while keeping soft touching and pushing. Obviously, the soft pushing is con...

show abstract

Robot box-pushing with environment-embedded sensors

Cited by 8 publications

References 7 publications

Multi-robot box-pushing in presence of measurement noise

Multi-robot box-pushing in presence of measurement noise

Behavior-based Robot Control Using Fuzzy Discrete Event System

Soft Pushing Operation with Dual Compliance Controllers Based on Estimated Torque and Visual Force

Contact Info

Product

Resources

About