Paper Link: coming! | TUSK Github: coming!
This paper extends prior work on untangling long cables and presents TUSK (Tracing to Untangle Semi-planar Knots), a learned cable-tracing algorithm that resolves over- crossings and undercrossings to recognize the structure of knots and grasp points for untangling from a single RGB image. This work focuses on semi-planar knots, which are knots composed of crossings that each include at most 2 cable segments. We conduct experiments on long cables (3 m in length) with up to 15 semi-planar crossings across 6 different knot types. Crops of crossings from 3 knots (overhand, figure 8, and bowline) of the 6 are seen during training, but none of the full knots are seen during training. This is an improvement from prior work on long cables that can only untangle 2 knot types. Experiments find that in settings with multiple identical cables, TUSK can trace a single cable with 81% accuracy on 7 new knot types. In single-cable images, the TUSK can trace and identify the correct knot with 77% success on 3 new knot types. We incorporate TUSK into a bimanual robot system and find that it successfully untangles 64% of cable configurations, including those with new knots unseen during training, across 3 levels of difficulty.
TUSK first performs cable tracing (1, 2). The trace is shown through a rainbow gradient (from violet to purple), depicting the sequence in which the cable is traced. After tracing, TUSK does crossing recognition (3) to obtain the full topology of the cable. Next, using crossing cancellation rules from knot theory, it analytically determines knots (4) in the cable. Next, TUSK surveys possible cage-pinch points (5) and selects the best candidate points to grasp to execute a cage-pinch dilation action, untangling the knot (6).
We first detect the endpoints and initialize the tracer with start points. If we are not able to obtain start points, we perturb the endpoint and try again. Next, we trace. While tracing, if the cable exits the workspace, we pull the cable towards the center of the workspace. If the tracer gets confused and begins retracing a knot region, we perform a partial cage-pinch dilation that will loosen the knot, intended to make the configuration easier to trace on the next iteration. If the trace is able to successfully complete, we analyze the topology. If there are no knots, we are done. If there are knots, we perform a cage-pinch dilation and return to the first step.
Tier A3 results are not shown as that tier is all fake knots.
Table of cables tested on, as well as their properties.
We test the neural network for tracing out of the box on the 5 new cables on overhand, figure 8, overhand honda, and bowline knots. Results are shown in the above table.
Overhand
Figure 8
Overhand Honda
Bowline
Linked Overhand
Figure 8 Honda
Bowline & Overhand Honda
Figure 8 Honda & Overhand