Touchless Telerobotic Surgery — Is It Possible at All?
Authors: Tian Zhou, Maria Cabrera, Juan Wachs
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Two experiments were conducted to measure the performance of different interfaces through teleoperation. Subjects used different interfaces to complete two surgical tasks while several task-related metrics were measured and further analyzed. |
| Researcher Affiliation | Academia | Tian Zhou, Maria E. Cabrera and Juan P. Wachs* School of Industrial Engineering, Purdue University. West Lafayette, IN {zhou338, cabrerm, jpwachs}@purdue.edu |
| Pseudocode | No | The paper describes some algorithmic steps in text (e.g., "piece-wise linear transformation", "inverse kinematics"), but it does not provide any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about open-sourcing code or links to repositories. |
| Open Datasets | No | The paper describes an experiment involving subjects and tasks to generate data, but it does not use a publicly available dataset, nor does it provide access information for the data collected. |
| Dataset Splits | No | The paper describes how data was collected and analyzed from experiments (e.g., "20 observations for each interface", "each trial was compared against a reference line"), but it does not specify typical train/validation/test dataset splits as used for model training. |
| Hardware Specification | No | The paper mentions the "Taurus robot" and input devices like "Kinect & Leap motion", "keyboards and haptic controllers (Omega & Hydra)", but it does not specify the computing hardware (e.g., CPU, GPU, memory) used to run the experiments or process data. |
| Software Dependencies | No | The paper mentions the hardware used (Taurus robot, Kinect, Leap Motion, Omega, Hydra) but does not list any specific software dependencies or libraries with version numbers (e.g., Python, PyTorch, operating system versions). |
| Experiment Setup | Yes | Two experiments were conducted to measure the performance of different interfaces through teleoperation. Subjects used different interfaces to complete two surgical tasks while several task-related metrics were measured and further analyzed. The first task involved conducting a guided surgical incision while maintaining a fixed depth. The second task involved a Peg Transfer task common in laparoscopic surgery skill assessment. Both tasks are shown in Figure 2. For the experimental design, ten engineering students conducted this experiment (5 male, 5 female, average age 30.5). Each subject teleoperated Taurus using two out of five interfaces, for five repetitions with each interface, resulting in 20 observations for each interface. The order of the two interfaces was randomized to compensate for the learning of the task. In the Incision Task, each trial was compared against a reference line (Figure 3, left) by selecting twenty equally spaced landmarks and finding the closest distance to the actual trajectory. All those results are averaged to get the deviation error per interface, as shown in Figure 3 (right). In order to measure how well the users could maintain a fixed depth, the variance of the depth trajectory was analyzed. The average of all the trials indicates the depth fluctuation per interface, as shown in Figure 4. In the Peg Transfer Task, the metrics recorded and analyzed were the task completion time and the number of peg drops. A learning rate was calculated after fitting learning curves to the completion time, shown in Table 1. |