Blind bulldozing: multiple robot nest construction

Emergent behavior in swarm robotic systems is key to obtaining complex behavior by a group of relatively simple agents. The question is how to design the individual behaviors of agents in such a way that the desired global behavior emerges. Different approaches have been proposed to solve this problem: from biologically inspired probabilistic behavioral models to evolutionary techniques. In some situations, however, creating a complex probabilistic model of the behavior or developing a proper setup for an evolutionary process can be challenging. In this paper we propose a new method, based on supervised learning on a relatively small number of training samples. We apply our method to the well-known clustering problem and show that this approach yields the desired global clustering behavior.

show abstract

“…Similar to [21], our agents have no specialized grippers to manipulate the pucks. Rather, the agents push the pucks with a plow.…”

Section: Methodsmentioning

confidence: 99%

Supervised Learning in Robotic Swarms: From Training Samples to Emergent Behavior

Vorobyev

Vardy

Banzhaf

2014

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

show abstract

“…Though it is generally unclear how to extend these to the distributed setting. Larger groups have been studied using a behavior-based framework ( [7], [9], [16]), but no attempt at formal grasp synthesis was made. Two very closely related works on distributed swarm manipulation are [21], and [17].…”

Section: A Decentralized Approachesmentioning

confidence: 99%

Distributed grasp synthesis for swarm manipulation with applications to autonomous tugboats

Esposito

2008

2008 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Assume a swarm of mobile robots is in the act of transporting a large object in the plane, by applying unilateral forces to the perimeter of that object. We address the question of where a new robot, joining the group, should establish contact with the object to maximally improve the manipulation capabilities of the swarm. Inspired by the literature on multi-fingered hands, we synthesize a grasp by incrementally optimizing a grasp quality function. We adapt the quality function in several important ways to accommodate the distributed nature of the swarm problem. We show that the objective function is quasiconcave, which has important implications for uniqueness and scalability of the solution; and present a solution methodology. We apply the resulting framework to the example of a large swarm of autonomous tug boats towing a barge, taken from our larger research program.

show abstract

“…Manipulation by autonomous ground vehicles has been examined before in the context of single robots or small groups of two to three robots (Lynch, 1999;Rus, 1997;Stilwell & Bay, 1994;Sugar & Kumar, 2002). However, for manipulation by groups of arbitrary sizes only two methods exist: behavior based-approaches (Ijspeert, Martinoli, Billard, & Gambardella, 2001;Kube & Bonabeau, 2000;Parker, Zhang, & Kube, 2005;Song & Kumar, 2002), which lack performance guarantees; and "kinematic caging" (Pereira, Kumar, & Campos, 2004;Sudsang & Ponce, 2005;Wang, Nakano, & Takahashi, 2003), which ignore second-order forces and actuator saturation. Purely kinematic approaches are not suitable for marine systems.…”

Section: Introductionmentioning

confidence: 99%

Comprehensive framework for tracking control and thrust allocation for a highly overactuated autonomous surface vessel

Feemster

Esposito

2010

Journal of Field Robotics

View full text Add to dashboard Cite

In this paper, we present a comprehensive trajectory tracking framework for cooperative manipulation scenarios involving marine surface ships. Our experimental platform is a small boat equipped with six thrusters, but the technique presented here can be applied to a multiship manipulation scenario such as a group of autonomous tugboats transporting a disabled ship or unactuated barge. The primary challenges of this undertaking are as follows: (1) the actuators are unidirectional and experience saturation; (2) the hydrodynamics of the system are difficult to characterize; and (3) obtaining acceptable performance under field conditions (i.e., global positioning system errors, wind, waves, etc.) is arduous. To address these issues, we present a framework that includes trajectory generation, tracking control, and force allocation that, despite actuator limitations, results in asymptotically convergent trajectory tracking. In addition, the controller employs an adaptive feedback law to compensate for unknown-difficult to measure-hydrodynamic parameters. Field trials are conducted utilizing a 3-m vessel in a nearby estuary. Published

show abstract

Blind bulldozing: multiple robot nest construction

Cited by 50 publications

References 8 publications

Supervised Learning in Robotic Swarms: From Training Samples to Emergent Behavior

Supervised Learning in Robotic Swarms: From Training Samples to Emergent Behavior

Distributed grasp synthesis for swarm manipulation with applications to autonomous tugboats

Comprehensive framework for tracking control and thrust allocation for a highly overactuated autonomous surface vessel

Contact Info

Product

Resources

About