Predict the Swing, Match the Speed: Robotic Pipe Stabbing With Learned Stereo
Overview
arXiv abstract (Oct 28) introduces StabBot, a robotic system using stereo vision and residual RL to predict pipe swings. Claims 100% success in controlled tests with reduced force vs conventional methods, validated via Froude-scaled MuJoCo model. No field deployment or license evidence reported yet. Latest: arXiv abstract published Oct 28, 2026 (arXiv:2610.37535v1). Claims 100% success in controlled experiments using stereo vision and residual RL to predict pipe swings and match speed for precise insertion. Results validated with a Froude-scaled MuJoCo model. No field deployment or license evidence reported yet. Latest: arXiv abstract published Oct 28, 2026 (arXiv:2610.37535v1). Claims 100% success in controlled experiments using stereo vision and residual RL to predict pipe swings and match speed for precise insertion. Results validated with a Froude-scaled MuJoCo model. No field deployment or license evidence reported yet.
Generated from attributed reports · Updated 28 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · pipe location error: 0.4 other · Basis not reported
“d every joint with the pipe touching only rollers, against 74% for a conventional fixed guide. Median contact speed fell from 18.4 to 2.3 cm/s and median peak head-pipe force from 11.3 to 1.4 kN, and the force was lower in all 200 jobs (Wilcoxon $p < 10^{-30}$). The network locates the pipe with 0.4-mm median error in 2.3 ms per stereo pair. With the network in the loop, success stayed at 100% under 20 mm of added no”
Exact source · revision 1Source owner not reported
Reported quantity · number of jobs: 200 other · Basis not reported
“es in at matched velocity, confirms the last millimetres by touch, aims the pin over the box when the elevator hangs off centre, and follows the block down with lateral compliance. A ResNet-18 keypoint network locates the pipe, pin nose and box mouth in 3-D, and a residual reinforcement-learning policy refines the capture. On 200 paired random jobs with nine sizes from 2-3/8-in. tubing to 20-in. casing, StabBot seate”
Exact source · revision 1Source owner not reported
Reported quantity · casing size: 20 other · Basis not reported
“es in at matched velocity, confirms the last millimetres by touch, aims the pin over the box when the elevator hangs off centre, and follows the block down with lateral compliance. A ResNet-18 keypoint network locates the pipe, pin nose and box mouth in 3-D, and a residual reinforcement-learning policy refines the capture. On 200 paired random jobs with nine sizes from 2-3/8-in. tubing to 20-in. casing, StabBot seate”
Exact source · revision 1Source owner not reported
Evidence dependency changes (1)
- 2026-10-30T17:34:49.405Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalPredict the Swing, Match the Speed: Robotic Pipe Stabbing With Learned Stereo Vision and Residual Reinforcement Learning
StabBot, a robotic stabbing system, uses stereo vision and residual reinforcement learning to predict pipe swings and adjust speed for precise insertion. It achieves 100% success in controlled experiments, reducing contact speed and force compared to conventional methods. Results are validated using a Froude-scaled MuJoCo model.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).