AutoCam: Hierarchical Path Planning for an Autonomous Auxiliary Camera in Surgical Robotics

Incorporating an autonomous auxiliary camera into robot-assisted minimally invasive surgery (RAMIS) enhances spatial awareness and eliminates manual viewpoint control. Existing path planning methods for auxiliary cameras track two-dimensional surgical features without simultaneously accounting for camera orientation, workspace constraints, and robot joint limits. This study introduces AutoCam: a system for automatic auxiliary camera placement to improve visualization in RAMIS. Implemented on the da Vinci Research Kit, AutoCam uses a priority-based, workspace-constrained controller that combines heuristic geometric placement with nonlinear optimization to ensure robust tracking. A user study (N=6) demonstrated that the system achieved 99.84% visibility of a salient feature, a pose error of 1.71 ± 1.54 degrees and 4.98 ± 5.00 mm, and computational efficiency (6.8 ± 12.8 ms loop time). An additional pilot study (N=6), in which novices completed a Fundamentals of Laparoscopic Surgery task, suggests that users can teleoperate as effectively from AutoCam’s viewpoint as from the endoscope’s, while still benefiting from AutoCam’s improved visual coverage. These results indicate that an auxiliary camera can be autonomously controlled using the da Vinci patient-side manipulators to track a salient feature, laying the groundwork for new multi-camera visualization methods in RAMIS. The open-source code for AutoCam is available at: RCL Autocam Public.git.