Mechanoreception for Soft Robots via Intuitive Body Cues

Wang, Liangliang; Wang, Zheng

doi:10.1089/soro.2018.0135

Cited by 36 publications

(28 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic tensegrity structures constitute an active and very flexible motile organization, which requires suitable (and complex) coordinative control to maintain body shape [ 74 , 77 ] and organize behaviour [ 3 , 5 , 22 ] as also can be witnessed in work on soft robotics [ 78 – 80 ].…”

Section: Reafferent Sensing and Body Deformationmentioning

confidence: 99%

Reafference and the origin of the self in early nervous system evolution

Jékely

Godfrey‐Smith

Keijzer

2021

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

Discussions of the function of early nervous systems usually focus on a causal flow from sensors to effectors, by which an animal coordinates its actions with exogenous changes in its environment. We propose, instead, that much early sensing was reafferent ; it was responsive to the consequences of the animal's own actions. We distinguish two general categories of reafference—translocational and deformational—and use these to survey the distribution of several often-neglected forms of sensing, including gravity sensing, flow sensing and proprioception. We discuss sensing of these kinds in sponges, ctenophores, placozoans, cnidarians and bilaterians. Reafference is ubiquitous, as ongoing action, especially whole-body motility, will almost inevitably influence the senses. Corollary discharge—a pathway or circuit by which an animal tracks its own actions and their reafferent consequences—is not a necessary feature of reafferent sensing but a later-evolving mechanism. We also argue for the importance of reafferent sensing to the evolution of the body-self , a form of organization that enables an animal to sense and act as a single unit. This article is part of the theme issue ‘Basal cognition: multicellularity, neurons and the cognitive lens’.

show abstract

Section: Reafferent Sensing and Body Deformationmentioning

confidence: 99%

Reafference and the origin of the self in early nervous system evolution

Jékely

Godfrey‐Smith

Keijzer

2021

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

show abstract

“…The setup we considered consists of an RGB camera and a proprioceptive gripper, which are equipped on the robot arm. The robot arm is controlled by an operator acting on a master device and interacting with the environment by combining the proprioception of our soft gripper (Wang and Wang, 2020 ) and the visual cues from the camera view. The relative coordinates of the camera and the testbed are first calibrated, and the depth is accordingly computed.…”

Section: System Architecturementioning

confidence: 99%

“…Then a robust object tracking algorithm continuously works to provide real-time visual cues for failure detection and recovery, even if the object is highly obstructed in the camera view. Meanwhile, the proprioceptive capability of our soft gripper (Wang and Wang, 2020 ) is utilized in the system to sense the contact between the object and the gripper. We measure the actuation pressure in the soft actuator chambers to extract the external contact force and further reflect the contact status between the gripper and object.…”

Section: System Architecturementioning

confidence: 99%

“…We especially focus on the failure detection and recovery framework in the grasping system by combining the specific proprioceptive capability of our soft gripper and the visual cues from the highly obstructed view when the failure occurs. The proprioceptive soft gripper used in the paper was developed in our recent work (Wang and Wang, 2020 ). It was pneumatically driven by soft bellows actuator and the pressure of the actuator was leveraged for sensing the gripper movement and external contact (see Figure 5 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Failure Handling of Robotic Pick and Place Tasks With Multimodal Cues Under Partial Object Occlusion

et al. 2021

Self Cite

View full text Add to dashboard Cite

The success of a robotic pick and place task depends on the success of the entire procedure: from the grasp planning phase, to the grasp establishment phase, then the lifting and moving phase, and finally the releasing and placing phase. Being able to detect and recover from grasping failures throughout the entire process is therefore a critical requirement for both the robotic manipulator and the gripper, especially when considering the almost inevitable object occlusion by the gripper itself during the robotic pick and place task. With the rapid rising of soft grippers, which rely heavily on their under-actuated body and compliant, open-loop control, less information is available from the gripper for effective overall system control. Tackling on the effectiveness of robotic grasping, this work proposes a hybrid policy by combining visual cues and proprioception of our gripper for the effective failure detection and recovery in grasping, especially using a proprioceptive self-developed soft robotic gripper that is capable of contact sensing. We solved failure handling of robotic pick and place tasks and proposed (1) more accurate pose estimation of a known object by considering the edge-based cost besides the image-based cost; (2) robust object tracking techniques that work even when the object is partially occluded in the system and achieve mean overlap precision up to 80%; (3) contact and contact loss detection between the object and the gripper by analyzing internal pressure signals of our gripper; (4) robust failure handling with the combination of visual cues under partial occlusion and proprioceptive cues from our soft gripper to effectively detect and recover from different accidental grasping failures. The proposed system was experimentally validated with the proprioceptive soft robotic gripper mounted on a collaborative robotic manipulator, and a consumer-grade RGB camera, showing that combining visual cues and proprioception from our soft actuator robotic gripper was effective in improving the detection and recovery from the major grasping failures in different stages for the compliant and robust grasping.

show abstract

“…Dynamic tensegrity structures constitute an active and very flexible motile organization, which requires suitable (and complex) coordinative control to maintain body shape [74] [77] and organize behaviour [22][3] [5] as also can be witnessed in work on soft robotics [78][79] [80].…”

Section: Animal Bodies As Tensegrity Structuresmentioning

confidence: 99%

Reafference and the origin of the self in early nervous system evolution

Jékely¹,

Godfrey‐Smith²,

Keijzer³

2020

Preprint

View full text Add to dashboard Cite

Discussions of the function of early nervous systems usually focus on a causal flow from sensors to effectors, by which an animal coordinates its actions with exogenous changes in its environment. We propose, instead, that much early sensing was reafferent; it was responsive to the consequences of the animal's own actions. We distinguish two general categories of reafference – translocational and deformational – and use these to survey the distribution of several often-neglected forms of sensing, including gravity sensing, flow sensing, and proprioception. We discuss sensing of these kinds in sponges, ctenophores, placozoans, cnidarians and bilaterians. Reafference is ubiquitous, as ongoing action, especially whole-body motility, will almost inevitably influence the senses. Corollary discharge – a pathway or circuit by which an animal tracks its own actions and their reafferent consequences – is not a necessary feature of reafferent sensing but a later- evolving mechanism. We also argue for the importance of reafferent sensing to the evolution of the body-self, a form of organization that enables an animal to sense and act as a single unit.

show abstract

Mechanoreception for Soft Robots via Intuitive Body Cues

Cited by 36 publications

References 44 publications

Reafference and the origin of the self in early nervous system evolution

Reafference and the origin of the self in early nervous system evolution

Failure Handling of Robotic Pick and Place Tasks With Multimodal Cues Under Partial Object Occlusion

Reafference and the origin of the self in early nervous system evolution

Contact Info

Product

Resources

About