tactile sensing
In plain wordsGiving robots a sense of touch, with sensors in fingertips or skin that feel pressure, texture, vibration and slipping, so they can handle objects gently and securely.
The measurement of physical contact between a robot and objects — where contact occurs, normal and shear forces, pressure distribution, vibration, slip, texture and sometimes temperature — using sensors in fingertips, grippers or artificial skin. Transduction methods include piezoresistive, capacitive, piezoelectric, magnetic and optical sensing. Vision-based tactile sensors such as GelSight and DIGIT put a camera behind a soft, coated elastomer and infer contact geometry and forces from images of its deformation, giving very high spatial resolution at low cost; because their output is an image, they suit deep learningdeep learning, n.: Machine learning done with neural networks built from many stacked layers: raw data such as pixels, sound or text goes in at one end, and each layer turns what it receives into something more abstract.. Touch supplies what cameras cannot during manipulationmanipulation, n.: A robot's use of arms, hands or grippers to change the world around it: picking things up, moving, pushing, opening, assembling or using tools.: contact state when the hand hides the object, and properties such as weight, stiffness and friction. It enables slip detection, gentle grasping of fragile items, insertion and in-hand dexterous manipulationdexterous manipulation, n.: Skilled handling of objects with robot fingers, such as spinning a pen, turning a key or rotating a cube in one hand: the fine finger work people do without thinking.. Barriers to wide use include durability, wiring, calibration drift and the difficulty of simulating touch for sim-to-real transfersim-to-real transfer, n.: Training a robot's AI in a computer simulation, where practice is fast, cheap and safe, and then making it work on the real robot despite the differences between simulation and reality.; adding touch to robot foundation modelsrobot foundation model, n.: One large AI model trained on huge amounts of robot and internet data so that it can control many robots on many tasks, and be adapted quickly to new ones. is an active research area.
With tactile sensing the gripper feels the glass start to slip and tightens before it falls.
Origin
Robot touch has been studied since the 1970s and 1980s, with Leon Harmon's 1982 survey setting early requirements. Micah Johnson and Edward Adelson's GelSight (MIT, 2009) introduced high-resolution vision-based tactile sensing, and Mike Lambeta and colleagues' low-cost DIGIT sensor (Facebook AI Research, 2020) spread it through robot learning.
Related
- dexterous manipulationdexterous manipulation, n.: Skilled handling of objects with robot fingers, such as spinning a pen, turning a key or rotating a cube in one hand: the fine finger work people do without thinking.
- graspinggrasping, n.: How a robot picks up and holds an object securely with a gripper or hand: deciding where to put its fingers or suction cup and how hard to squeeze.
- proprioceptionproprioception, n.: A robot's sense of its own body: where its joints are, how fast they are moving and how hard its motors are pushing, measured by internal sensors rather than cameras.
- end effectorend effector, n.: The tool at the end of a robot arm that actually touches the world, such as a gripper, suction cup, welding torch, paint sprayer or robotic hand.
- manipulationmanipulation, n.: A robot's use of arms, hands or grippers to change the world around it: picking things up, moving, pushing, opening, assembling or using tools.
- sensor fusionsensor fusion, n.: Combining readings from several different sensors, such as cameras, radar, lidar, GPS and motion sensors, to get a more accurate and reliable picture than any one sensor gives alone.
Sources
- Johnson, M. K. & Adelson, E. H. (2009). Retrographic sensing for the measurement of surface texture and shape. Proc. IEEE CVPR 2009.
- Lambeta, M. et al. (2020). DIGIT: A novel design for a low-cost compact high-resolution tactile sensor with application to in-hand manipulation. IEEE Robotics and Automation Letters 5(3).
Mentioned in
end effectorend effector, n.: The tool at the end of a robot arm that actually touches the world, such as a gripper, suction cup, welding torch, paint sprayer or robotic hand., graspinggrasping, n.: How a robot picks up and holds an object securely with a gripper or hand: deciding where to put its fingers or suction cup and how hard to squeeze., manipulationmanipulation, n.: A robot's use of arms, hands or grippers to change the world around it: picking things up, moving, pushing, opening, assembling or using tools., perceptionperception, n.: How an AI system or robot turns raw sensor signals, such as camera pixels, microphone sound or laser scans, into an understanding of what is around it: objects, people, words and distances., dexterous manipulationdexterous manipulation, n.: Skilled handling of objects with robot fingers, such as spinning a pen, turning a key or rotating a cube in one hand: the fine finger work people do without thinking., impedance controlimpedance control, n.: A way of controlling a robot so that it behaves like a spring and shock absorber when it touches things, giving way gently instead of pushing rigidly., proprioceptionproprioception, n.: A robot's sense of its own body: where its joints are, how fast they are moving and how hard its motors are pushing, measured by internal sensors rather than cameras.