Chinese Journal of Intelligent Science and Technology ›› 2022, Vol. 4 ›› Issue (2): 186-199.doi: 10.11959/j.issn.2096-6652.202222

• Special Topic: Autonomous Agent Learning for Dexterous and Accurate Manipulations • Previous Articles     Next Articles

A survey of visuotactile sensing technologies for robotic manipulation

Shaowei CUI1,2, Shuo WANG1,3,4, Jingyi HU1,2, Chaofan ZHANG1,3   

  1. 1 The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
    2 School of Future Technology, University of Chinese Academy of Sciences, Beijing 100049, China
    3 School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
    4 Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai 200031, China
  • Online:2022-06-15 Published:2022-06-01
  • Supported by:
    The National Key Research and Development Program of China(2018AAA0103003)


Thanks to the high spatial resolution and multi-mode tactile sensing, visuotactile sensing technology has been widely applied to various robotic manipulation tasks, such as robotic active perception, pose estimation, and in-hand manipulation.Firstly, the current mainstream visuotactile sensing technologies based on sensing principles were summarized, which could be mainly divided into three categories: GelSight-type visuotactile sensors, binocular (multi-view) visuotactile sensors, and other types.Meanwhile, the sensing methods of different tactile sensing modes were further summarized, including contact surface 3D geometry, force/torque, and sliding.Furthermore, focusing on the field of robot operation, the specific application scenarios of visuotactile sensors were discussed.Finally, future work of the visuotactile sensing technology and how they can be further applied to robotic dexterous manipulation tasks were given.

Key words: visuotactile sensor, robotic tactile perception, robotic dexterous manipulation

CLC Number: 

No Suggested Reading articles found!