Robust Autonomous Control of a Magnetic Millirobot in In Vitro Cardiac Flow
arXiv:2604.01523v1 Announce Type: new Abstract: Untethered magnetic millirobots offer significant potential for minimally invasive cardiac therapies; however, achieving reliable autonomous control in pulsatile cardiac flow remains challenging. This work presents a vision-guided control framework enabling precise autonomous navigation of a magnetic millirobot in an in vitro heart phantom under physiologically relevant flow conditions. The system integrates UNet-based localization, A* path planning, and a sliding mode controller with a disturbance observer (SMC-DOB) designed for multi-coil electromagnetic actuation. Although drag forces are estimated using steady-state CFD simulations, the controller compensates for transient pulsatile disturbances during closed-loop operation. In static flu
View PDF HTML (experimental)
Abstract:Untethered magnetic millirobots offer significant potential for minimally invasive cardiac therapies; however, achieving reliable autonomous control in pulsatile cardiac flow remains challenging. This work presents a vision-guided control framework enabling precise autonomous navigation of a magnetic millirobot in an in vitro heart phantom under physiologically relevant flow conditions. The system integrates UNet-based localization, A* path planning, and a sliding mode controller with a disturbance observer (SMC-DOB) designed for multi-coil electromagnetic actuation. Although drag forces are estimated using steady-state CFD simulations, the controller compensates for transient pulsatile disturbances during closed-loop operation. In static fluid, the SMC-DOB achieved sub-millimeter accuracy (root-mean-square error, RMSE = 0.49 mm), outperforming PID and MPC baselines. Under moderate pulsatile flow (7 cm/s peak, 20 cP), it reduced RMSE by 37% and peak error by 2.4$\times$ compared to PID. It further maintained RMSE below 2 mm (0.27 body lengths) under elevated pulsatile flow (10 cm/s peak, 20 cP) and under low-viscosity conditions (4.3 cP, 7 cm/s peak), where baseline controllers exhibited unstable or failed tracking. These results demonstrate robust closed-loop magnetic control under time-varying cardiac flow disturbances and support the feasibility of autonomous millirobot navigation for targeted drug delivery.*
Subjects:
Robotics (cs.RO)
Cite as: arXiv:2604.01523 [cs.RO]
(or arXiv:2604.01523v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2604.01523
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Anuruddha Bhattacharjee [view email] [v1] Thu, 2 Apr 2026 01:48:04 UTC (5,378 KB)
Sign in to highlight and annotate this article

Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
announceautonomousarxiv
Exploring Early Web Patterns for Modern AI Agent Development
Exploring Early Web Patterns for Modern AI Agent Development The repository 6551Team/claude-code-design-guide presents an interesting thesis: visual and architectural solutions from the early web - from first HTML pages to 1990s browser interfaces - can enrich modern AI agent development using Claude Code. The Connection Isn't Forced Early internet had to solve problems similar to today's AI agency challenges: Constrained client resources Need for fast content delivery Operating under unstable connections These solutions - interface design patterns, data structures, state management approaches - were largely forgotten, though some are precisely suited for the new generation of autonomous systems. ## Practical Guide, Not Just History The project isn't merely historical reference; it's a pra
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.





Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!