Abstract
The picking performance of a robot can be severely affected by measurement errors, especially when handling objects that are fragile or irregular in shape and size. This is one of the main reasons that the problem of autonomously picking and placing objects is not solved. In this article, we exploit the "embodied" intelligence of soft robotic technologies to propose an integrated system, named SoftHandler, capable of overcoming some of the limitations of traditional pick-and-place industrial robots. The SoftHandler (Figure 1) integrates a novel parallel soft manipulator, the SoftDelta, and a novel soft end effector, the Pisa/(Istituto Italiano di Tecnologia) IIT SoftGripper.
Highlights
The picking performance of a robot can be severely affected by measurement errors, especially when handling objects that are fragile or irregular in shape and size
We propose exploiting the properties of articulated soft robots by merging a soft manipulator and soft end effector to develop a device that is suitable in a set of scenarios characterized by imprecise knowledge of the position, shape, and weight of movable objects and the environment
To establish a baseline for the evaluation of the SoftHandler performance, we developed a benchmark task and compared an equivalent rigid manipulator based on the same architecture of the SoftDelta but actuated by rigid motors
Summary
The picking performance of a robot can be severely affected by measurement errors, especially when handling objects that are fragile or irregular in shape and size. Soft robots (both soft continuum [1] and soft articulated [2]) include system-embedding compliant elements within their design Such systems show an adaptive behavior that is useful for interacting with unknown objects [3] or environments [4], and they are robust to impacts [5]. We propose exploiting the properties of articulated soft robots by merging a soft manipulator and soft end effector to develop a device that is suitable in a set of scenarios characterized by imprecise knowledge of the position, shape, and weight of movable objects and the environment. Top-down grasping approaches are usually favored for these common logistic tasks, based on how humans perform
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call