proprioception
In plain wordsA 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.
- 1
Robotics
Sensing of a robot's own internal state — joint angles and velocities from encoders, motor currents and joint torques, forces at the wrists and feet, and body orientation and acceleration from an inertial measurement unit — as opposed to exteroception, which senses the outside world through cameras, lidarlidar, n.: A sensor that measures distances by firing laser pulses and timing their reflections, building a 3D picture of its surroundings out of millions of points; widely used on robots and self-driving cars., microphones or touch. Proprioceptive signals arrive quickly, are reliable and are unaffected by lighting or occlusion, so they anchor low-level control and state estimation, and learned policiespolicy, n.: An AI agent's strategy: the rule it follows to pick an action in each situation. Training in reinforcement learning means improving this rule until it earns high rewards. and vision-language-action modelsvision-language-action model, n.: An AI model that looks through a robot's cameras, reads an instruction such as 'put the cup in the sink', and turns both straight into the robot's movements. typically take a proprioceptive state vector alongside camera images. Legged robotslegged robot, n.: A robot that walks on legs instead of rolling on wheels, such as a four-legged 'robot dog' or a two-legged humanoid, so it can climb stairs and cross rough ground. can walk 'blind' over rough terrain from proprioception alone, inferring contact and slip from joint torques, and so-called proprioceptive actuatorsactuator, n.: The 'muscle' of a machine: a motor or similar device that turns electrical, hydraulic or air power into movement, such as turning a robot's joint or closing its gripper. use low gear ratios so that motor current reveals external forces.
The policy takes two camera images plus a 14-dimensional proprioception vector of joint angles.
- 2
Biology
The sense of the position, movement and effort of one's own body parts, served by receptors in muscles, tendons and joints; it lets people touch their nose with their eyes closed and is the model for the robotics usage.
Origin
Coined by the physiologist Charles Sherrington in 1906, from Latin proprius, 'one's own', and reception; he contrasted proprioceptive with exteroceptive and interoceptive senses. Robotics adopted the proprioceptive/exteroceptive distinction for classifying sensors, and it is standard in mobile-robotics textbooks.
Related
- tactile sensingtactile sensing, n.: Giving 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.
- 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.
- actuatoractuator, n.: The 'muscle' of a machine: a motor or similar device that turns electrical, hydraulic or air power into movement, such as turning a robot's joint or closing its gripper.
- legged robotlegged robot, n.: A robot that walks on legs instead of rolling on wheels, such as a four-legged 'robot dog' or a two-legged humanoid, so it can climb stairs and cross rough ground.
- odometryodometry, n.: Estimating how far and in which direction a robot or vehicle has moved by adding up its own motion, such as wheel turns or how camera images shift, like counting your steps.
- embodied cognitionembodied cognition, n.: The idea that thinking is not something the brain does on its own: the body, its senses and movements, and its surroundings play a real part in how we think and understand.
- 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.
Sources
- Sherrington, C. S. (1906). The Integrative Action of the Nervous System. Yale University Press.
Mentioned in
actuatoractuator, n.: The 'muscle' of a machine: a motor or similar device that turns electrical, hydraulic or air power into movement, such as turning a robot's joint or closing its gripper., legged robotlegged robot, n.: A robot that walks on legs instead of rolling on wheels, such as a four-legged 'robot dog' or a two-legged humanoid, so it can climb stairs and cross rough ground., 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., 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., odometryodometry, n.: Estimating how far and in which direction a robot or vehicle has moved by adding up its own motion, such as wheel turns or how camera images shift, like counting your steps., tactile sensingtactile sensing, n.: Giving 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.