Why Highly Precise Robots Sometimes Fail at Assembly
Sent Oct 15, 2026
Beyond precise position control, toward robots that detect contact and adapt flexibly
💡 This Week’s Newsletter Summary
- Why Even High-Precision Robots Fail at Assembly: High repeatability and vision AI alone are insufficient to resolve minute positioning errors during the assembly process, and forcing precise positioning can lead to damage to the parts.
- Toward Robots That Detect and Adapt to Contact: Technology that combines impedance control, force and torque sensors, and AI learning to flexibly adjust movement and stiffness based on contact conditions is gaining attention.
Robotic arms are already precise enough—so what’s the problem?
The first industrial robot, Unimate, began working at a GM plant in 1961. Since then, robotic arms have been replacing humans in tasks such as welding, painting, and material handling, and their precision has reached an astonishing level.

Industrial Robot Arm Welding Line
However, we must pay close attention to the word “repeatability” here. This precision refers to the robot’s ability to return exactly to coordinates that have been pre-programmed (taught) by a human; it does not imply the ability to adapt its movements to unfamiliar situations. Without separate recognition or correction functions, even if a part is placed just a few millimeters off-center on the conveyor belt, the robot will reach for the original coordinates.
Therefore, rather than making “robots smarter,” traditional factory automation has actively utilized an approach of “adapting the environment to the robot” by using separate devices to consistently fix the position and orientation of parts. While this approach is effective on production lines that mass-produce the same product, it reaches its limits in high-mix, low-volume production or unstructured tasks where the product changes frequently.
Wouldn’t installing a camera solve the problem?

Box Pick-and-Place Using a Robotic Arm
The first solution that comes to mind is equipping robots with eyes. This involves using vision AI to determine the position and orientation of parts and control the robot’s movements accordingly. For example, there is a task that involves recognizing the location of a box and picking it up to move it.

Example of a “Peg-in-Hole” Assembly
The challenge lies in precision assembly. If factors such as camera calibration, object recognition, and the robot’s absolute positional error overlap, the final position may be off. In tasks such as connector insertion or bearing shaft assembly, the clearance between parts can be as small as tens of micrometers—narrower than the thickness of a human hair. This is why, no matter how precisely one looks, it is difficult to achieve the final alignment based solely on visual inspection.
Why Rigid Robots Are Actually More Dangerous
This reveals a more fundamental problem. Traditional robotic arms primarily use position control to precisely track the target position. But what happens if the robot continues to push a part into place without adjusting its movement in response to contact, even when the part is slightly misaligned? Even a small positional discrepancy can generate significant force, causing the part to jam, get scratched, or—in severe cases—break.
People behave differently. When plugging in a USB drive, we don’t precisely calculate the position of the port. We hold it roughly in place, wiggle it slightly, and tilt it, using the “feel” at our fingertips to find the right spot. The human hand isn’t fixated on a specific position; it possesses a “softness” that allows it to naturally pull back when it encounters resistance.
Treating Robots Like Springs: Impedance Control

Schematic Diagram of Impedance Control (Spring-Damper Model)
A prime example of how this smoothness is achieved is impedance control, a method systematized by Neville Hogan of MIT in 1985. Rather than forcibly maintaining the target position, it causes the system to respond like a “virtual spring and damper.”
Stiffness: The further one strays from the goal, the greater the force that tries to pull one back
Damping: The faster the motion, the more it is damped
This way, when the robot encounters a part, it does not simply push forward blindly but responds flexibly to external forces. By combining this with appropriate insertion motions or exploration strategies, it can compensate for minor positional errors and successfully insert the part.
A similar concept can be found in the RCC (Remote Center Compliance) device developed by the Draper Laboratory in the United States in the 1970s. This method uses the elastic structure of the robot’s wrist to help align parts with holes. While the RCC achieved flexibility through a mechanical structure, impedance control differs in that it regulates the relationship between motion and force.
The Remaining Challenge: “How Soft Should It Be?”
However, impedance control also presents its own challenges. Success or failure depends on how the stiffness is set. If it is too stiff, the component may break; if it is too soft, there may not be enough force, resulting in a failed insertion or the component being pushed into the wrong position.
What makes it even more challenging is that the appropriate stiffness varies at each stage of the process. It must be fast and precise during movement, gentle enough to absorb shock upon initial contact with a part, and the stiffness must be adjusted according to the direction during insertion. Traditionally, skilled engineers had to manually tune the control parameters, which was one of the hidden costs of assembly automation.
AI Controls the Sensation in the Fingertips
This is precisely where AI is gaining attention as a new solution. Of course, AI isn’t strictly necessary for adjusting stiffness. It’s possible to pre-program the mechanism to move gently during contact and firmly during insertion. However, it’s difficult to design rules every time the characteristics of the parts or the contact conditions change.
Consequently, recent research has focused on using signals from force and torque sensors (F/T sensors) or tactile sensors on robotic wrists to enable AI to learn movements and stiffness appropriate to the situation. This approach is related to Variable Impedance Learning and is being actively researched in the field of robotic manipulation involving frequent contact.

A robot that utilizes both vision AI and force control
By applying this approach, AI in manufacturing environments can perform the following roles:
- Vision (vision AI): Identifies where components are located and in what orientation, and determines their insertion positions.
- Fingertips (Force Control + Learning): It corrects minute errors—down to the last 1 mm—in response to contact and adjusts the required force and stiffness to ensure a precise fit.
Robot AX: Beyond Precise Movement, Toward Flexible Adaptation
As robots become increasingly capable of sensing contact with precision and sensitivity while independently regulating their force, this adaptability will become a key driver of advancements in manufacturing AX.