Trajectory Divergence Horizon Decision for Reliable Dual-Arm Surgical Subtask Manipulation
2026-08-10 • Robotics
Robotics
AI summaryⓘ
The authors focus on improving surgical robots that learn tasks by combining vision, language, and action (VLA models). They identified a problem where these robots follow fixed action plans that can fail if conditions change unexpectedly during surgery. To fix this, they created a method called TDHD that lets the robot decide when to stop and replan based on detecting unreliable actions. Testing on a real robot system showed that this adaptive approach made the robot better at needle and tissue tasks, especially in tricky final steps. This work suggests that flexible control is key for safe and reliable surgical robot automation.
surgical robotic systemsVision-Language-Action (VLA) modelsadaptive executiontrajectory divergenceflow matchingneedle manipulationtissue manipulationreplanningdual-arm benchmarkteleoperated demonstrations
Authors
Mingwu Su, Guankun Wang, Jinsong Lin, Rulin Zhou, Ziyi Hao, Zhiwei Fang, Huxin Gao, Jiewen Lai, Jiazheng Wang, Fan Zhang, Hongliang Ren
Abstract
Surgical robotic systems are increasingly being adopted as clinical workload rises, motivating autonomous solutions for repetitive manipulation subtasks. Learning-based controllers improve generalization compared with rule-based and analytic approaches, but most are trained for individual tasks and remain difficult to reuse across procedures. Vision-Language-Action (VLA) models provide a unified framework that integrates visual perception, language grounding, and action generation, offering a promising path toward more composable surgical autonomy. However, existing VLA policies rely on fixed-length open-loop action sequences, where changing scene conditions can lead to accumulated errors and potential risks in surgical manipulation. To mitigate this issue, we formulate surgical VLA deployment as an adaptive execution-horizon decision problem and propose Trajectory Divergence Horizon Decision (TDHD), a test-time mechanism that estimates step-wise action reliability by measuring the divergence between two flow-matching-generated trajectories under small noise perturbations and truncates execution using a dual-threshold rule to trigger timely replanning. We further establish a real-world da Vinci-like dual-arm benchmark with synchronized multi-view perception and language instructions, and collect 600 teleoperated demonstrations across needle (reach, pick, regrasp) and tissue (reach, lift, resection) manipulation suites. On real hardware with 20 trials per task setting, TDHD consistently improves performance over the latest VLA baselines: success increases from 55\% to 60\% for needle manipulation and from 55\% to 80\% for tissue manipulation, with the largest gains observed in the final manipulation stages. These results highlight the importance of adaptive execution control for reliable deployment of VLA models in surgical robotic manipulation.