Cal-MR

NEW CAL-MR SITE UNDER CONSTRUCTION


Cal-MR: Center for Automation and Learning for Medical Robotics

UC Berkeley's Center for Automation and Learning for Medical Robotics (Cal-MR) advances research in automation and machine learning to improve robots and devices for medicine and surgery.

Cal-MR is co-directed by Profs. Pieter Abbeel (EECS) and Ken Goldberg (IEOR, EECS, School of Information, Art Practice at UC Berkeley, and Department of Radiation Oncology at UCSF) and Researcher Dr. Sachin Patil. Cal-MR, established in Nov 2014, is based in the College of Engineering at UC Berkeley and is funded by a major grant from the National Science Foundation (NSF), from companies including Intuitive Surgical and Google, and from private donors. Cal-MR supports research with postdocs, grads, and undergraduate students and collaborations with leading physicians and researchers at UC San Francisco, UC Davis, UC Santa Cruz, University of Washington, Johns Hopkins, and Stanford.

Recent News

  • Ken Goldberg in MIT Tech Review

    Nimble-Fingered Robot Outperforms the Best Human Surgeons

  • Cal-MR presents at ICRA 2016

    1. TSC-DL: Unsupervised Trajectory Segmentation of Multi-Modal Surgical Demonstrations with Deep Learning.
    2. Autonomous Multiple-Throw Multilateral Surgical Suturing with a Mechanical Needle Guide and Optimization based Needle Planning.

  • CNET News: How robots could be your future surgeons

  • Autonomous Robot Surgery: Performing Surgical Subtasks without Human Intervention

    Automating repetitive surgical subtasks such as suturing, cutting and debridement can reduce surgeon fatigue and procedure times and facilitate supervised tele-surgery. Programming is difficult because human tissue is deformable and highly specular. Using the da Vinci Research Kit (DVRK) robotic surgical assistant, we explore a “Learning By Observation” (LBO) approach where we identify, segment, and parameterize sub-trajectories (“surgemes”) and sensor conditions to build a finite state machine (FSM) for each subtask. The robot then executes the FSM repeatedly to tune parameters and if necessary update the FSM structure.

    We evaluate the approach on two surgical subtasks: debridement of 3D Viscoelastic Tissue Phantoms (3d-DVTP), in which small target fragments are removed from a 3D viscoelastic tissue phantom, and Pattern Cutting of 2D Orthotropic Tissue Phantoms (2d-PCOTP), a step in the standard Fundamentals of Laparoscopic Surgery training suite, in which a specified circular area must be cut from a sheet of orthotropic tissue phantom. We describe the approach and physical experiments, which yielded a success rate of 96% for 50 trials of the 3d-DVTP subtask and 70% for 20 trials of the 2d-PCOTP subtask.

    For more details, please refer to the paper: [pdf]

    Press: New York Times, Medgadget

  • OSTP/NRI Workshop: Brainstorming Workshop on Safety Robotics for Ebola Workers

    Friday Nov 7 2014; 8am - 1 pm, PST (invitation only)
    Locations: White House Office of Science and Technology Policy (OSTP), Worcester Polytechnic Institute; Texas A&M; University of California, Berkeley;

    This one-day, invitation-only exploratory workshop aims to understand how tele-robots and related technologies might assist patients and healthcare and laboratory workers. The goal is to identify both near-term and longer-term research needs.

    Press: New York Times

Cal-MR | 2111 Etcheverry Hall | Berkeley, CA

under construction