Robot Jenga: Autonomous and strategic block extraction

Wang, Jiuguang; Rogers, Philip; Parker, Lonnie T.; Brooks, Douglas; Stilman, Mike

doi:10.1109/iros.2009.5354303

Cited by 17 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In research of Wang [3]et aI., 8 blocks in 9 layers are candidate of removing. In their experiment with 20 trials, maximum number of removed block is 5 and average is 2.7.…”

Section: Discussionmentioning

confidence: 99%

“…If it senses large force or look the tower leans, the robot changes to another block randomly. Wang et al [3] also uses a vision sensor. By the vision sensor, robot checks a motion of other blocks during removing a block and achieves safe extraction.…”

Section: Related Workmentioning

confidence: 99%

“…First one IS removing only by robot manipulator. In the previous research of Wang [3], they evaluate their system by number of successfully removed blocks by removing only by a robot. So, we also count the number of removed blocks before tower breaking or failure of operation.…”

Section: A Removing By Robotmentioning

confidence: 99%

See 2 more Smart Citations

Force based manipulation of Jenga blocks

Kimura

Watanabe

Aiyama

2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Our goal is to copy human dexterity of manipula tion with force feeling to robot manipulation. We adopt Jenga game as our first target task. This paper describes our strategic implementation how robot removes blocks from Jenga tower.In this paper, we make Jenga kinematics model. First we show kinematics model of stable Jenga tower. Another kinematics model is of transition period of removing block. Using these kinematics models, robot manipulator chooses the most safe block to remove. But of course, there exist difference of acting force between ideal model and actual Jenga tower. So the robot judges the acting force against ideal one whether the block can be removed or not. When it is judged not to remove, the robot changes to next candidate to remove. According this force based manipulation strategy, the robot has achieved to remove more than twelve blocks form Jenga block tower. During competition with human, the robot can remove a block after more than twenty blocks are removed.

show abstract

“…In research of Wang [3]et aI., 8 blocks in 9 layers are candidate of removing. In their experiment with 20 trials, maximum number of removed block is 5 and average is 2.7.…”

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Force based manipulation of Jenga blocks

Kimura

Watanabe

Aiyama

2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…None of these works consider stability during construction. The work that most resembles ours is seen in [22], where a robot successfully deconstructs a tower of rectangular blocks. The blocks to be removed are chosen by a set of heuristics and the choices are analyzed for stability with a physics-based simulation.…”

Section: A Related Workmentioning

confidence: 99%

Assembly path planning for stable robotic construction

McEvoy

Komendera

Correll

2014

2014 IEEE International Conference on Technologies for Practical Robot Applications (TePRA)

View full text Add to dashboard Cite

We propose an algorithmic approach for assembly path planning that takes stability of the structure during construction into account. Finite Element Analysis (FEA) is used to evaluate the intermediate stages of the assembly for stability. The algorithm presented here assembles a structure by greedily taking the most stable option at each step in the assembly process, and has complexity O(n!), albeit most structures are effectively assembled with complexity O(n 2 ). We demonstrate the workings of the proposed hybrid discrete/FEA search algorithm in simulation on a series of truss structures. In particular, we show that the algorithm is able to identify correct orderings that led to stable assembly, and discuss structures for which a greedy approach with scaffolding might be advantageous over a complete approach.

show abstract

“…In our work the fixed support is considered as a hand, so there is only one moving hand. The stability analysis we perform also has potential applications for assistive robots in domestic environments, where tasks like stacking books, dishes, boxes, and even blocks (e.g., in the game Jenga [24]) are common. It may also be useful for autonomous construction [10], and safe removal of collapsed structures during rescue operations after disasters such as earthquakes.…”

Section: Introductionmentioning

confidence: 99%

The Influence of Motion Path and Assembly Sequence on Stability of Assemblies

Rakshit

Akella

2013

Robotics: Science and Systems IX

View full text Add to dashboard Cite

Abstract-In this paper we present an approach for the stability analysis of mechanical part disassembly considering part motion in the presence of physical forces such as gravity and friction. Our approach uses linear complementarity to analyze stability as parts are moved out of the assembly. As each part is removed from the assembly along a specified path during disassembly, we compute the contact forces between parts in the remaining assembly; positive contact forces throughout the disassembly process imply the disassembly sequence is stable (since the parts remain in contact with one another). However, if the part that is being taken out induces motion of other parts in the remaining subassembly, we conclude the disassembly sequence is unstable. Thus, we are able to simulate the entire disassembly sequence considering physical forces and part motion, which has not previously been done. We then show the influence of part motion on the selection of stable disassembly sequences. In contrast to prior work on disassembly which has focused either on planning part motions based on only geometric constraints, or on analyzing the stability of an assembly without considering part motions, we explore the relation between part motion and the selection of stable disassembly sequences. Since we track the motion of all parts in an assembly, instability inducing motions can be identified and prevented by introducing appropriate fixtures, by selecting alternative disassembly sequences, or by changing the motion paths. We also describe when the presence of physical forces can make assembly and disassembly noninvertible, i.e., disassembly is not the inverse of assembly.

show abstract

Robot Jenga: Autonomous and strategic block extraction

Cited by 17 publications

References 10 publications

Force based manipulation of Jenga blocks

Force based manipulation of Jenga blocks

Assembly path planning for stable robotic construction

The Influence of Motion Path and Assembly Sequence on Stability of Assemblies

Contact Info

Product

Resources

About