Shared Haptic Control for Surgical Skill Transfer on a Dual-Console Da Vinci Research Kit
Xiangyi Le, Nan Jiang, Pucheng Shao, Brendan Burkhart, Peter Kazanzides, Ugur Tumerdem
AI summary
Problem
Current robotic surgery training isolates trainees and lacks haptic feedback, while existing dual-console systems only switch control rather than dynamically sharing it with kinesthetic coupling.
Approach
The authors implemented a four-channel multilateral teleoperation architecture on a dual-console da Vinci Research Kit, using learning-based sensorless force estimation to allow an expert and novice to dynamically share motion and force authority via an adjustable dominance factor.
Key results
- Sub-millimeter position (≤0.2 mm) and force (≤1 N) tracking errors in transparency tests
- 83% single-user and 74% dual-user tumor detection accuracy in blind palpation tasks
- Novices significantly reduced suture force error and increased safe-range time after expert-guided training
- First implementation of multilateral haptic shared control on a clinical da Vinci platform
Why it matters
Provides a feasible, real-time haptic training paradigm for surgical education, addressing the critical gap in hands-on skill transfer for robotic surgery residents.
Abstract
Robotic surgery has revolutionized minimally in- vasive procedures by offering enhanced precision, dexterity, and patient outcomes. However, the training and operational paradigms in robotic surgery have not evolved in parallel. Current apprenticeship models fall short in this domain, as robotic surgery isolates the primary surgeon in a teleoperated control loop, limiting opportunities for hands-on learning by trainees. To address this, we present the first implementation of a multilateral controller on a da Vinci Research Kit (dVRK), en- abled by a four-channel teleoperation architecture and learning- based force estimation on a dual-console setup. This framework allows an expert and novice to share motion and force authority on the patient side robots through an adjustable dominance factor. We validated the system in three experiments. In transparency tests, the architecture achieved sub-millimeter position tracking errors (PTE ≤0.2 mm) and force tracking errors (FTE ≤1 N). In a palpation pilot user study (N=10) with tumor-tissue phantoms, participants identified stiffer regions, without visual feedback, with 83% accuracy in single-user mode (α = 1) and 74% accuracy in dual-user shared mode (α = 0.5). In a suturing force control pilot user study (N=10), novices significantly reduced force error and increased time within the safe range after expert-guided training, with no suture breakage observed post-training. These results on a dual- console dVRK setup demonstrate the feasibility of expert-in- the-loop training with real-time haptic guidance, positioning multilateral teleoperation as a promising approach for surgical skill transfer.