A survey of robotic caging and its applications

Makita, Satoshi; Wan, Weiwei

doi:10.1080/01691864.2017.1371075

Cited by 50 publications

(36 citation statements)

References 119 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 17b shows using the closed distal phalanx to grasp a cup having a lifting ear. This kind of grasping mode is similar to caging [29,30]. Figure 17c shows how to grasp objects with a cone shape.…”

Section: Linkage-driven Gripper Experimentsmentioning

confidence: 98%

Design and Implementation of a Multi-Function Gripper for Grasping General Objects

et al. 2019

View full text Add to dashboard Cite

The development of a reliable pick-and-place system for industrial robotics is facing an urgent demand because many manual-labor works, such as piece-picking in warehouses and fulfillment centers tend toward automation. This paper presents an integrated gripper that combines a linkage-driven underactuated gripper with a suction gripping system for picking up a variety of objects in different working environments. The underactuated gripper consists of two fingers, and each finger has three degrees of freedom that are obtained by stacking one five-bar mechanism over one double parallelogram. Furthermore, each finger is actuated by two motors, both of which can be installed at the base owing to the special architecture of the proposed robotic finger. A suction cup is used to grasp objects in narrow spaces and cluttered environments. The combination of the suction and traditional linkage-driven grippers allows stable and reliable grasping under different working environments. Finally, practical experiments using a wide range of objects and under different grasping scenarios are performed to demonstrate the grasping capability of the integrated gripper.

show abstract

Section: Linkage-driven Gripper Experimentsmentioning

confidence: 98%

Design and Implementation of a Multi-Function Gripper for Grasping General Objects

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Using the Q single -network with a probability of ψ, each robot can take approaching and transport actions from the beginning (lines [12][13][14][15]. With the help of the actions by Q single -network, multiple robots can train their network Q multi (lines [16][17][18][19][20]. The rest of the algorithm is similar to that of the region-growing curriculum (Section 6.1) except the concatenation of states.…”

Section: Single-to Multi-robot Curriculummentioning

confidence: 99%

“…However, the information of the surrounding environment, such as the static friction between an object and ground, object shape, or geometrical structures, should be known in advances. Finally, the caging method combines the advantages of robust manipulation in the grasping method and flexible object transportation in the pushing method [ 8 , 19 , 20 ]. Multiple robots approach an object and enclose it to prevent escape from robot formation.…”

Section: Related Workmentioning

confidence: 99%

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Eoh

Park

2021

Sensors

View full text Add to dashboard Cite

This paper presents a cooperative object transportation technique using deep reinforcement learning (DRL) based on curricula. Previous studies on object transportation highly depended on complex and intractable controls, such as grasping, pushing, and caging. Recently, DRL-based object transportation techniques have been proposed, which showed improved performance without precise controller design. However, DRL-based techniques not only take a long time to learn their policies but also sometimes fail to learn. It is difficult to learn the policy of DRL by random actions only. Therefore, we propose two curricula for the efficient learning of object transportation: region-growing and single- to multi-robot. During the learning process, the region-growing curriculum gradually extended to a region in which an object was initialized. This step-by-step learning raised the success probability of object transportation by restricting the working area. Multiple robots could easily learn a new policy by exploiting the pre-trained policy of a single robot. This single- to multi-robot curriculum can help robots to learn a transporting method with trial and error. Simulation results are presented to verify the proposed techniques.

show abstract

“…The principle to determine the middle node is to guarantee that the length of L sim denoted by l sim , the length of L ms(i+1) denoted by l ms(i+1) and the length of caging edge K i ∼ K i+1 denoted by l i(i+1) satisfy the constructive condition of triangle, i.e., the sum of any two sides of a triangle is greater than the third side and the difference of any two sides of a triangle is less than the third side. According to the cosine law, the angle between L sim and K i ∼ K i+1 denoted by γ i1 , and the angle between L sim and l ms(i+1) denoted by γ i2 are as shown in (13) and (14), respectively. The signs and concrete values of J si and J mi are determined by the rotation direction.…”

Section: ) the Strategy Of One Caging Edge Matchmentioning

confidence: 99%

“…Then, a good condition for grasping and manipulating the dysfunctional satellite is created, in which the dysfunctional satellite cannot escape from the encirclement formed by the hyper-redundant manipulator, even if there is unexpected collision between the dysfunctional satellite and the hyper-redundant manipulator. The most striking feature of caging is that it is assumed to be accomplished only by position-controlled agents without considering mechanical properties like contact and forces, which relaxes control during the caging process [12]- [14]. Therefore, compared with current dysfunctional satellite capturing and removal methods (e.g.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Caging Configuration Design Algorithm of Hyper-Redundant Manipulator for Dysfunctional Satellite Pre-Capture

2020

View full text Add to dashboard Cite

This paper presents an adaptive caging configuration design algorithm of the hyper-redundant manipulator for dysfunctional satellite pre-capture. Taking advantages of the extreme flexibility and hyperredundancy, the hyper-redundant manipulator wraps its whole body around the dysfunctional satellite to restrain its motion without requiring grappling points and accurate information. However, the hyperredundancy also makes the caging configuration design more complicated and challenging. In this paper, the dynamic sequential caging following algorithm based on rapidly-exploring random tree algorithm is proposed to search the caging configuration in real-time. First, according to the discretized caging trace, which is twining around the grasped object and selected based on the caging conditions, the joints of the hyper-redundant manipulator are divided into several groups in advance. Then, the joint angles are searched group by group to realize the match of the discretized caging trace by the hyper-redundant manipulator. As a result, the configuration between the grasped object and the hyper-redundant manipulator satisfies the caging conditions. The main advantages of the proposed caging motion planning algorithm lie in the avoidance of the inversion and the efficiency of computation. Finally, the pre-capture of two dysfunctional satellites with different shapes using a twenty universal joint manipulator is implemented, and the simulation results verify the efficiency of the proposed method. INDEX TERMS Caging configuration design, hyper-redundant manipulator, caging trace, dynamic sequential caging following algorithm, rapidly-exploring random tree.

show abstract

A survey of robotic caging and its applications

Cited by 50 publications

References 119 publications

Design and Implementation of a Multi-Function Gripper for Grasping General Objects

Design and Implementation of a Multi-Function Gripper for Grasping General Objects

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Adaptive Caging Configuration Design Algorithm of Hyper-Redundant Manipulator for Dysfunctional Satellite Pre-Capture

Contact Info

Product

Resources

About