Autonomous Robotic Navigation for Endovascular Brain-Computer Interface Access
Authors: Harry Robertshaw, Weijie Qi, Nikola Fischer, Alejandro Granados, Thomas C. Booth, Sam E. John
Organizations: School of Biomedical Engineering & Imaging Sciences, Kings College London, London, UK · Department of Biomedical Engineering, The University of Melbourne, Parkville, Victoria, Australia · Department of Neuroradiology, King’s College Hospital, London, UK
Endovascular brain-computer interfaces (BCIs) avoid craniotomy but require precise device delivery through anatomically variable cerebral veins. This work presents the first demonstration of in vitro autonomous robotic navigation for endovascular BCI access in the cerebral venous system. Soft Actor-Critic controllers were trained in silico for two sequential tasks spanning the right internal jugular vein to the superior sagittal sinus, using geometric augmentation of one training anatomy. Navigation was evaluated in a training anatomy and an anatomically unseen hold-out model over 250 in silico episodes and five fluoroscopy-guided in vitro robotic runs per task-anatomy condition, comprising 1,000 simulated episodes and 20 physical runs overall. Task recurrent predictors were also evaluated for online identification of impending navigation failure. In silico success rates for Tasks A and B were 85.6% and 98.4% in the training anatomy and 42.0% and 91.6% in the hold-out anatomy, respectively. Fourteen of 20 physical runs were successful (70% overall), including 80% success for Task B in the hold-out phantom. In silico the predictors detected 99.3-100.0% of failures with false-alarm rates of 0.8-6.7%. During in vitro evaluation, predicted risk increased before failed episodes, but elevated probabilities during some successful runs showed reduced calibration after transfer. These results demonstrate the feasibility of autonomous cerebral venous access and show how online failure prediction could support human oversight, while also identifying anatomical generalization and sim-to-real calibration as priorities before preclinical translation.
Figures & tables
Figure 1: Labeled anatomy for navigation tasks A and B, with task start and target region highlighted.
Anatomy
Task
Length (mm)
Tortuosity
Training
A
224.6
1.72
Training
B
145.4
1.49
Hold-out
A
211.9
1.73
Hold-out
B
161.3
1.39
Table 1: Centreline length and tortuosity for each anatomy and task. Length was calculated as the sum of the Euclidean distances between consecutive centreline points. Tortuosity was calculated as the centreline length divided by the straight-line distance between the first and last centreline points; a value of 1 indicates a straight path.
Figure 2: Labeled in vitro testbed, with inset of 3D vascular phantom and labeled anatomy.
Figure 3: Robotic manipulator used for in vitro evaluation.
Figure 4: Failure predictor architecture, comprising the recurrent input sequence, 128-unit GRU, prediction head, and sigmoid output estimating failure probability within the next H=20 control steps.
Parameter
Value
Learning rate
2.20×10−4
Discount factor ( γ )
0.99
Batch size
32
Replay buffer size
104
Training steps
2×107
Heat-up steps
5×105
Table 2: In silico training hyperparameters.
Figure 5: Phantom vessel model under fluoroscopy, showing start and target regions for task A and B.
Anatomy
Task
Success rate (%, 95% CI)
Path ratio (%)
Procedure time (s)
Training
A
85.6 (214/250, 80.7–89.4%)
13.7 ± 23.2
10.33 ± 4.60
Training
B
98.4 (246/250, 96.0–99.4%)
31.7 ± 4.5
13.40 ± 5.64
Hold-out
A
42.0 (105/250, 36.0–48.2%)
8.4 ± 1.4
12.15 ± 6.44
Hold-out
B
91.6 (229/250, 87.5–94.4%)
30.2 ± 19.3
11.77 ± 5.74
Table 3: In silico navigation performance across anatomy and task conditions. Values are reported over 250 episodes per condition. Path ratio is summarized over unsuccessful episodes, and procedure time over successful episodes. Continuous values are mean ± SD.
Anatomy
Task
Detection (%, 95% CI)
Lead time (steps)
False alarm (%, 95% CI)
Brier score
Training
A
100.0 (36/36, 90.4–100.0%)
23.0 [21.8, 24.0]
2.3 (5/214, 1.0–5.4%)
0.0032±0.0122
Training
B
100.0 (4/4, 51.0–100.0%)
22.0 [21.5, 22.5]
0.8 (2/246, 0.2–2.9%)
0.0003±0.0018
Hold-out
A
99.3 (144/145, 96.2–99.9%)
27.0 [26.0, 28.0]
6.7 (7/105, 3.3–13.1%)
0.0203±0.0212
Hold-out
B
100.0 (21/21, 84.5–100.0%)
22.0 [20.0, 29.0]
0.9 (2/229, 0.2–3.1%)
0.0026±0.0103
Table 4: Failure-predictor performance in silico . Proportion confidence intervals are Wilson 95% CIs. Warning lead time is median [IQR], and Brier score is mean ± SD.
Figure 6: Temporal failure-prediction performance, across training and hold-out anatomies. Mean predictor outputs are shown for unsuccessful episodes aligned to failure (left) and successful episodes aligned to completion (right). Time is normalized to episode duration. Solid and dashed curves are in silico and in vitro episodes, respectively; shaded regions show 95% CIs.
Anatomy
Task
Success rate (%)
Path ratio (%)
Procedure time (s)
Training
A
80 (4/5)
84 ( n=1 )
188±96
Training
B
80 (4/5)
35 ( n=1 )
85±29
Hold-out
A
40 (2/5)
88±10
101±33
Hold-out
B
80 (4/5)
56 ( n=1 )
93±56
Table 5: In vitro navigation performance across anatomy and task conditions. Each condition comprised five runs. Path ratio is summarized over unsuccessful runs, and procedure time over successful runs. Continuous values are mean ± SD.
Figure 7: Spatial distribution of predictor-triggered guidewire-retraction onsets during armed navigation in the hold-out in vitro anatomy. Heatmap intensity indicates the relative frequency of retraction onset.
Robotic endovascular intervention uses robotic systems to navigate vascular instruments and perform procedures with greater precision, control, or autonomy.
Autonomous mechanical thrombectomy (MT) presents substantial challenges due to highly variable vascular geometries and the requirements for accurate, real-time control. While reinforcement learning (RL) has emerged as a promising paradigm for the automation of endovascular navigation, existing approaches often show limited robustness when faced with diverse patient anatomies or extended navigation horizons. In this work, we investigate a world-model-based framework for autonomous endovascular navigation built on TD-MPC2, a model-based RL method that integrates planning and learned dynamics. We evaluate a TD-MPC2 agent trained on multiple navigation tasks across hold out patient-specific vasculatures and benchmark its performance against the state-of-the-art Soft Actor-Critic (SAC) algorithm agent. Both approaches are further validated in vitro using patient-specific vascular phantoms under fluoroscopic guidance. In simulation, TD-MPC2 demonstrates a significantly higher mean success rate than SAC (58% vs. 36%, p < 0.001), and mean tip contact forces of 0.15 N, well below the proposed 1.5 N vessel rupture threshold. Mean success rates for TD-MPC2 (68%) were comparable to SAC (60%) in vitro, but TD-MPC2 achieved superior path ratios (p = 0.017) at the cost of longer procedure times (p < 0.001). Together, these results provide the first demonstration of autonomous MT navigation validated across both hold out in silico data and fluoroscopy-guided in vitro experiments, highlighting the promise of world models for safe and generalizable AI-assisted endovascular interventions.
Harry Robertshaw, Nikola Fischer, Han-Ru Wu +6
Surgical & Interventional Engineering, School of Biomedical Engineering & Imaging Sciences, King’s College London, UK · Department of Radiology, National Taiwan University Hospital, Taiwan · Department of Neuroradiology, King’s College Hospital, UK
Mechanical thrombectomy (MT) is typically the optimal treatment for acute ischemic stroke involving large vessel occlusions, but access is limited due to geographic and logistical barriers. Reinforcement learning (RL) shows promise in autonomous endovascular navigation, but generalization across 'long' navigation tasks remains challenging. We propose a Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL) framework for autonomous two-device navigation in vitro, enabling efficient and generalizable navigation. HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA). A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL. The framework was validated in both in silico and in vitro testbeds to assess generalization and real-world feasibility. In silico, a single-vasculature model achieved 92-100% success rates on individual anatomies, while a multi-vasculature model achieved 56-80% across multiple patient anatomies. In vitro, both HM-MARL models successfully navigated 100% of trials from the femoral artery to the right common carotid artery and 80% to the right ICA but failed on the left-side vessel superhuman challenge due to the anatomy and catheter type used in navigation. This study presents the first demonstration of in vitro autonomous navigation in MT vasculature. While HM-MARL enables generalization across anatomies, the simulation-to-real transition introduces challenges. Future work will refine RL strategies using world models and validate performance on unseen in vitro data, advancing autonomous MT towards clinical translation.
Harry Robertshaw, Nikola Fischer, Lennart Karstensen +6
School of Biomedical Engineering & Imaging Sciences, Kings College London, London, UK · School of Engineering & Materials Science, Queen Mary University of London, London, UK
Accurate intraoperative navigation is essential for robot-assisted endoluminal intervention, but remains difficult because of limited endoscopic field of view and dynamic artifacts. Existing navigation platforms often rely on external localization technologies, such as electromagnetic tracking or shape sensing, which increase hardware complexity and remain vulnerable to intraoperative anatomical mismatch. We present a vision-only autonomy framework that performs long-horizon bronchoscopic navigation using preoperative CT-derived virtual targets and live endoscopic video, without external tracking during navigation. The framework uses hierarchical long-short agents: a short-term reactive agent for continuous low-latency motion control, and a long-term strategic agent for decision support at anatomically ambiguous points. When their recommendations conflict, a world-model critic predicts future visual states for candidate actions and selects the action whose predicted state best matches the target view. We evaluated the system in a high-fidelity airway phantom, three ex vivo porcine lungs, and a live porcine model. The system reached all planned segmental targets in the phantom, maintained 80% success to the eighth generation ex vivo, and achieved in vivo navigation performance comparable to the expert bronchoscopist. These results support the preclinical feasibility of sensor-free autonomous bronchoscopic navigation.
Junyang Wu, Mingyi Luo, Fangfang Xie +7
Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, 200240, China. · Shanghai Chest Hospital, Shanghai, 10587, China.