Equation 1 · How Embodied AI Actually Works
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
This equation states an equality: the expressions on both sides have the same value under the article’s assumptions. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
Symbol τ
τ is part of the quantity the equation computes from the expression on the right.
Symbol K_p
is one of the signed contributions combined to compute the quantity on the left.
Symbol K_d
is one of the signed contributions combined to compute the quantity on the left.
Symbol q̇_d
q̇_d has a dot, marking the rate of change of the underlying indexed quantity with respect to the article’s time variable.
Symbol q̇
q̇ has a dot, marking the rate of change of the underlying indexed quantity with respect to the article’s time variable.
Symbol tau_ff
a feedforward term — gravity compensation, or a reaction-force term handed down from a higher-level controller — added on top.
=
The expressions on both sides represent the same quantity under the stated assumptions.
See an illustrated explanation →subtraction
Subtract the following term or group from the preceding one. A leading minus marks a negative quantity.
subscript
The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.
How to interpret it
Read it with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
The dominant scheme for the last stage is impedance control rather than pure position control, and the distinction matters for exactly the reason a robot has to touch things. A pure position controller tries to force a joint to a commanded angle regardless of what resists it, which is dangerous the instant the arm meets an object, a surface, or a person, because the controller will keep applying more torque to fight the very contact it should be responding to. An impedance controller instead makes the joint behave like a programmable spring and damper around the commanded target: . Here and q are the desired and measured joint positions, and set how stiff and…
Read the full surrounding passage
The dominant scheme for the last stage is impedance control rather than pure position control, and the distinction matters for exactly the reason a robot has to touch things. A pure position controller tries to force a joint to a commanded angle regardless of what resists it, which is dangerous the instant the arm meets an object, a surface, or a person, because the controller will keep applying more torque to fight the very contact it should be responding to. An impedance controller instead makes the joint behave like a programmable spring and damper around the commanded target: . Here and q are the desired and measured joint positions, and set how stiff and how damped that virtual spring-and-damper is, and is a feedforward term — gravity compensation, or a reaction-force term handed down from a higher-level controller — added on top. The learned policy’s contribution to this equation is : a target, updated at whatever rate the policy runs. Everything else in the equation runs at a much higher rate, underneath the policy, and it is what actually decides how the robot responds to unexpected resistance in the interval between two policy decisions. Lower the gains and the joint yields to contact instead of fighting it; that yielding, not any property of the learned policy, is most of what keeps a light unexpected collision from becoming a hard one.
Sources cited in the article section
These citations give research context. Read each source to check which claims it supports.
Return to How Embodied AI Actually Works