# ImitateCholec: A Multimodal Dataset for Long-Horizon Imitation Learning in Robotic Cholecystectomy

## TL;DR

ImitateCholec is a new dataset for training robotic systems to perform complex surgical tasks in cholecystectomy, using real-world data from porcine surgeries.

## Contribution

The dataset introduces a large-scale, multimodal resource for long-horizon imitation learning in robotic cholecystectomy.

## Key findings

- The dataset includes 18,000 demonstrations from 34 porcine surgeries, segmented into 17 surgical tasks.
- It combines endoscopic video and kinematic data to support robust imitation learning for autonomous robotic systems.
- The dataset enables training for phase-level autonomy and supports applications like error recognition and tool pose estimation.

## Abstract

The growing global shortage of skilled surgeons underscores the need for intelligent, assistive technologies in the operating room. To address this challenge, we introduce ImitateCholec, a publicly available dataset specifically designed to advance autonomous robotic systems during the critical clipping and cutting phase of laparoscopic cholecystectomy. The dataset comprises over 18,000 demonstrations from 34 ex vivo porcine cholecystectomies, totaling approximately 20 hours of data. Each clipping and cutting phase recorded in the dataset is segmented into 17 distinct surgical tasks. ImitateCholec uniquely integrates endoscopic videos captured from multiple camera perspectives with comprehensive kinematic data acquired through the da Vinci Research Kit. Both optimal demonstration executions and recovery maneuvers were systematically recorded, enabling the training of imitation learning models capable of robustly addressing real-world surgical variability. Primarily, ImitateCholec facilitates imitation learning for long-horizon surgical workflow execution, significantly advancing the development of autonomous robotic systems toward achieving phase-level autonomy and, ultimately, full procedural autonomy. Additional supported applications include surgical workflow modeling, error recognition, and surgical tool pose estimation.