A review on sensory perception for dexterous robotic manipulation

Abstract

Sensory perception for dexterous robotic hands is an active research area and recent progress in robotics. Effective dexterous manipulation requires robotic hands to accurately feedback their state or perceive the surrounding environment. This article reviews the state-of-the-art of sensory perception for dexterous robotic manipulation. Two types of sensors, such as intrinsic and extrinsic sensors, are introduced according to their function and layout in robotic hands. These sensors provide rich information to a robotic hand, which contains the posture, the contact information of objects, and the physical information of the environment. Then, a comprehensive analysis of perception methods including planning-level, control-level, and learning-level perceptions is presented. The information obtained from sensory perception can help robotic hands to make decisions effectively. Previously issued reviews mainly focus on the design of tactile senor, while we analyze and discuss the relationship among sensing, perception, and dexterous manipulation. Some potential research topics on sensory perception are also summarized and discussed.

A Framework for Relating Natural Movement to Length and Quality of Life in Human and Non-human Animals

“…It may, for example, be valuable to compare the complexity of movement produced by Parkinson’s Disease patients following different treatments, to help decide which was most effective. Finally, it is difficult to design robots to move with the level of complexity (e.g., dexterity) present in animals (Xia et al, 2022). M comp may be used to test and improve it.…”

“…Finally, it is difficult to design robots to move with the level of complexity (e.g., dexterity) present in animals (Xia et al, 2022). 𝑀 𝑐𝑜𝑚𝑝 may be used to test and improve it.…”

Multifunctional actuators integrated with the function of self-powered temperature sensing made with Ti3C2Tx–bamboo nanofiber composites

“…[13][14][15] In recent years, flexible actuators based on carbon nanomaterials, biomass nanomaterials, hydrogels, polymers, and other emerging materials have been developed. [16][17][18][19][20] For example, Feng et al developed a light-driven micro air vehicle with a bilayer structure by imitating the flight principle of Taraxacum in nature, realizing the precise control of the micro air vehicle by programming the material structure. 21 Hu et al utilized the excellent photo/ electro-thermal conversion efficiency of carbon nanotubes and the anisotropic thermal expansion performance of polyethylene to prepare a bilayer actuator.…”

Flexible Multimodal Sensor Based on Double‐network Hydrogel for Human and Robotic Applications

“…What is more, the tactile sensing system with tactile sensors as the core has become an essential part of the new intelligent robot, which is characterized by the robot touching to obtain a variety of physical information about the target object, to realize the robot's detection of the spatial state, contact state, and physical properties of the operating object, and extract the shape, quality, stiffness, temperature, and posture of the active thing, and other characteristics, and then feedback the valuable information to the robot control system, which processes and judges the information to make the corresponding feedback action. [23][24] Robotic hands with integrated multimodal sensors can grasp any object in a controlled manner using tactile feedback, which has great potential for applications in robotics. [25] For example, Kim et al [26] demonstrated smart prosthetic skin instrumented with ultrathin, single crystalline silicon nanoribbon strain, pressure and temperature sensor arrays, associated humidity sensors, electro-resistive heaters, and stretchable multi-electrode arrays for nerve stimulation, which hold far-reaching enlightenments for advanced prosthetics and robotics to mimic the behaviors of human skin.…”