AutoCam: Hierarchical Path Planning for an Autonomous Auxiliary Camera in Surgical Robotics (2505.10398v1)

Abstract: 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 but do not simultaneously account for camera orientation, workspace constraints, and robot joint limits. This study presents AutoCam: an automatic auxiliary camera placement method to improve visualization in RAMIS. Implemented on the da Vinci Research Kit, the system uses a priority-based, workspace-constrained control algorithm that combines heuristic geometric placement with nonlinear optimization to ensure robust camera tracking. A user study (N=6) demonstrated that the system maintained 99.84% visibility of a salient feature and achieved a pose error of 4.36 $\pm$ 2.11 degrees and 1.95 $\pm$ 5.66 mm. The controller was computationally efficient, with a loop time of 6.8 $\pm$ 12.8 ms. An additional pilot study (N=6), where novices completed a Fundamentals of Laparoscopic Surgery training task, suggests that users can teleoperate just as effectively from AutoCam's viewpoint as from the endoscope's while still benefiting from AutoCam's improved visual coverage of the scene. 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.

Hierarchical Path Planning for Autonomous Cameras in Surgical Robotics

The paper presents AutoCam, an innovative hierarchical path planning system designed to manage an autonomous auxiliary camera within the context of robot-assisted minimally invasive surgery (RAMIS). The primary aim is to enhance spatial awareness during surgery by automating camera control, which historically requires manual manipulation and can distract the surgical team. AutoCam is implemented on the da Vinci Research Kit, which integrates several advanced components to achieve robust camera tracking, improved viewpoint placement, and efficient path planning under various constraints.

Key Contributions and Findings

AutoCam introduces several novel strategies to optimize the placement and trajectory of auxiliary cameras in surgical environments:

1. Hierarchical Control Framework: The system starts with a naive geometric-based camera pose calculation, followed by smooth interpolations of this trajectory, incorporation of workspace constraints, and solving of inverse kinematics with joint limit consideration. This framework ensures that the camera tracks surgical features effectively while maintaining flexibility in movement.
2. Orientation Control and Pose Tracking: AutoCam successfully maintains a viewing vector angle error of 1.71° and a feature distance error of 4.98 mm, providing stable and accurate visualization. This precision is critical for maintaining focus on salient features during surgical procedures.
3. Constraint Handling and Optimization: By incorporating constrained optimization for inverse kinematics, AutoCam efficiently addresses challenges encountered when naive approaches fail, particularly in terms of joint limit constraints and workspace boundaries.
4. Computational Performance: The system maintains a loop time of 6.8 ms, indicating substantial computational efficiency, which is crucial for real-time surgical applications.
5. High Visibility Scores: The system achieved visibility of the salient feature 99.84% of the time during dry-lab evaluation, showcasing its ability to maintain visual continuity in complex and dynamic surgical environments.
6. Usability in Training: A pilot paper demonstrated comparable performance in task completion for novice surgeons using the autonomous camera compared to traditional single-view systems, with promising implications for surgical training, albeit with some variability in subjective task load assessments.

Implications and Future Directions

The practical implications of AutoCam in RAMIS are significant. The autonomous control of auxiliary cameras can reduce the cognitive and physical load on the surgical team, allowing them to focus more on intricate surgical tasks while benefiting from enhanced visualization across stereo perspectives. The technology may lead to more refined surgical practices with potential reductions in surgical errors and improved safety.

Theoretically, AutoCam's hierarchical control methods could pave the way for advancements in multi-camera systems beyond RAMIS, such as in other teleoperation domains requiring precise visual tracking and control in constrained environments. The integration of machine learning methods for feature tracking and scene reconstruction, combined with this hierarchical path planning approach, could further refine surgical aids and autonomous capabilities in next-generation robotic systems.

As surgery robotics continue to evolve, research can focus on integrating more complex perception algorithms that can adaptively manage camera viewpoints without human intervention. Future work might also explore scaling AutoCam's applications across different surgical systems or extending its real-world usage beyond dry-lab validation. Combining its control strategies with augmented reality and machine learning analytics could significantly bolster the autonomy and efficiency of surgical interventions in RAMIS and beyond.