A High-Payload Proprioceptive Hybrid Robotic Gripper With Soft Origamic Actuators

Su, Yinyin; Wang, Zheng; Fang, Zhonggui; Zhu, Wenpei; X, Sun; Zhu, Yuming; Wang, Hexiang; Tang, Kailuan; Huang, Hailin; Liu, Sicong

doi:10.1109/lra.2020.2974438

Cited by 35 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous extreme application scenarios in soft robotics field have shown the critical demand of a multifunctional integrated sensor unit for proprioception of the large continuum and multi-degree-of-freedom deformation, with ambient environmental information perception, such as the aquatic field with varying temperatures, etc. Apart from the stretching, twisting movements of the robots were shown to be difficult to measure, which is very common in robotic hand or joint motions (S. Liu et al, 2020 ; Su et al, 2020 ). The coupled deformation requires different sensing mechanisms leading to system bulkiness and complexity.…”

Section: Design and Modelingmentioning

confidence: 99%

A Multimodal Hydrogel Soft-Robotic Sensor for Multi-Functional Perception

Zhang

Zhu

et al. 2021

Front. Robot. AI

Self Cite

View full text Add to dashboard Cite

Soft robots, with their unique and outstanding capabilities of environmental conformation, natural sealing against elements, as well as being insensitive to magnetic/electrical effects, are ideal candidates for extreme environment applications. However, sensing for soft robots in such harsh conditions would still be challenging, especially under large temperature change and complex, large deformations. Existing soft sensing approaches using liquid-metal medium compromise between large deformation and environmental robustness, limiting their real-world applicability. In this work, we propose a multimodal solid-state soft sensor using hydrogel and silicone. By exploiting the conductance and transparency of hydrogel, we could deploy both optical and resistive sensing in one sensing component. This novel combination enables us to benefit from the in-situ measurement discrepancies between the optical and electrical signal, to extract multifunctional measurements. Following this approach, prototype solid-state soft sensors were designed and fabricated, a dedicated neural network was built to extract the sensory information. Stretching and twisting were measured using the same sensor even at large deformations. In addition, exploiting the distinctive responses against temperature change, we could estimate environmental temperatures simultaneously. Results are promising for the proposed solid-state multimodal approach of soft sensors for multifunctional perception under extreme conditions.

show abstract

Section: Design and Modelingmentioning

confidence: 99%

A Multimodal Hydrogel Soft-Robotic Sensor for Multi-Functional Perception

Zhang

Zhu

et al. 2021

Front. Robot. AI

Self Cite

View full text Add to dashboard Cite

show abstract

“…With unregulated, omni-directional passive compliance, soft actuators by default could not achieve directional actuation without being soft and flexible in other directions, therefore significantly hindering their levels of force payload and precision ( Zhou et al, 2018 ). Using rigid reinforcements on soft actuators could significantly constrain their compliance and achieve directionality during operation, the approach has been repeatedly proven using pneumatic soft robots as wearable devices and industrial grippers ( Zhou et al, 2018 ; Liu et al, 2020 ; Su et al, 2020 ), achieving dozens of times payload increase without sacrificing lightweightness. However, for underwater applications very little work was reported to date.…”

Section: Introductionmentioning

confidence: 99%

Underwater Crawling Robot With Hydraulic Soft Actuators

et al. 2021

Self Cite

View full text Add to dashboard Cite

Benthic operation plays a vital role in underwater applications, where crawling robots have advantages compared with turbine-based underwater vehicles, in locomotion accuracy, actuation efficiency, current resistance, and in carrying more payloads. On the other hand, soft robots are quickly trending in underwater robotic design, with their naturally sealed body structure and intrinsic compliance both desirable for the highly unstructured and corrosive underwater environment. However, the limitations resulting directly from the inherent compliance, in structural rigidity, actuation precision, and limited force exertion capability, have also restricted soft robots in underwater applications. To date soft robots are adopted mainly as grippers and manipulators for atraumatic sampling, rather than as locomotion platforms. In this work, we present a soft-robotic approach to designing underwater crawling robots, with three main innovations: 1) using rigid structural components to strategically reinforce the otherwise omni-directionally flexible soft actuators, drastically increasing their loading capability and actuation precision; 2) proposing a rigid–soft hybrid multi-joint leg design, with quasi-linear motion range and force exertion, while maintaining excellent passive impact compliance by exploiting the inherent flexibility of soft actuators; 3) developing a novel valve-free hydraulic actuation system with peristaltic pumps, achieving a compact, lightweight, and untethered underwater crawling robot prototype with a 5:1 payload-to-weight ratio and multi-gait capability. The prototype was tested for design verification and showcasing the advantages of the proposed hybrid mechanism and actuation approach.

show abstract

“…Meanwhile, under-actuated robotic grippers (Zhou et al, 2017 ) recently tend to have a variety of advantages over the rigid-bodied counterparts when the gripper is interacting with the environment. There are numerous grippers with novel designs of compliant mechanisms, working as both actuators and sensors to generate movement and provide proprioceptive feedback simultaneously (Su et al, 2020 ; Zhou et al, 2020 ). Endowing soft robotic grippers with proprioception enables reliable interactions with environment.…”

Section: Introductionmentioning

confidence: 99%

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

A High-Payload Proprioceptive Hybrid Robotic Gripper With Soft Origamic Actuators

Cited by 35 publications

References 24 publications

A Multimodal Hydrogel Soft-Robotic Sensor for Multi-Functional Perception

A Multimodal Hydrogel Soft-Robotic Sensor for Multi-Functional Perception

Underwater Crawling Robot With Hydraulic Soft Actuators

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

Contact Info

Product

Resources

About