EEmbodied AI Hub
IndustryProductEditor’s pick

Medtronic Readies Touch Surgery Aide Platform to Embed Real-Time AI Across the Surgical Workflow

Medtronic PLC is preparing to launch Touch Surgery Aide, an NVIDIA-powered AI compute platform that links pre-operative planning, intra-operative tele-mentoring, and post-operative insights inside a single ecosystem. The first cleared application, Instrument Exit Point (IEP), runs on the Hugo RAS system and delivers visual alerts when instruments leave the camera view. The move positions Medtronic to differentiate its Hugo platform through multimodal inference rather than hardware alone, while e

Medtronic Readies Touchrobotics-business

Source: Robotics Business Review · July 22, 2026

Share this article so more people can see it

Medtronic PLC is preparing to introduce Touch Surgery Aide, an AI compute platform built to run inside the operating room and connect every stage of a surgical case. The system forms the core of the Touch Surgery Ecosystem and is scheduled for an early showcase at the Society of Robotic Surgery 2026 Annual Meeting.

Touch Surgery Aide uses NVIDIA accelerated computing infrastructure, specifically Holoscan, CUDA, and TensorRT, to run multiple computer-vision and multimodal models simultaneously on live surgical video. The platform processes both visual feeds and procedural context in real time, generating actionable overlays without requiring surgeons to leave the sterile field.

The first cleared application is Instrument Exit Point (IEP), which received FDA clearance for use with the Hugo RAS system. IEP employs computer vision to detect when selected instruments move beyond the visible field and issues an immediate visual notification. This marks Medtronic’s initial step toward embedding real-time AI directly into robotic procedures.

Hugo itself has accumulated substantial clinical volume. The system received FDA clearance for urologic procedures in December 2025 and, by June 2026, Medtronic had filed 510(k) submissions to add general surgery and gynecologic indications. The robot has already been used in tens of thousands of cases across more than 35 countries.

Medtronic executives frame the platform as a shift from hand-assist technologies to team-level decision support. Chief technology officer Jim Peichel noted that real-time AI is moving surgery from tools that guide the hand to systems that help teams work faster and with greater situational awareness.

From a commercial standpoint, Touch Surgery Aide gives Medtronic a software layer that can be updated after hardware installation. Hospitals that purchase Hugo gain access to an expanding library of AI applications without additional capital equipment purchases, a model that contrasts with competitors whose AI features remain more tightly coupled to specific system generations.

The architecture also supports tele-mentoring and post-case review, allowing a single expert to oversee multiple rooms or review annotated video for quality improvement. This capability is particularly relevant for Medtronic’s stated goal of expanding access beyond high-volume academic centers.

Longer term, the company intends to extend the same compute platform from robotic-assisted cases into conventional laparoscopic procedures, broadening the addressable installed base. The combination of FDA-cleared hardware clearances, NVIDIA infrastructure, and a modular AI application model gives Medtronic a concrete path to increase procedure volume and recurring software value per installed Hugo system.

Related resources on this hub

Jump to projects, models, or datasets mentioned or closely related.

Discussion

Tell us what you think — comments make stories more useful for builders and founders.

Tell us what you think!

Medtronic Readies Touch Surgery Aide Platform to Embed Real-Time AI Across the Surgical Workflow

Have an account? Log in to use your display name and avatar.

Email is optional and never shown on the page.

More insights

IndustryProductFeaturedRobotics Business Review

Beyond the Hype: How Time Series Databases Are Solving Robotics' Real Data Bottlenecks

As robotics deployments scale, traditional relational databases like Postgres are hitting performance walls due to high-volume sensor data ingestion. Tiger Data’s TimescaleDB solves this by extending Postgres with time-series primitives and columnar storage, eliminating the need for complex secondary data pipelines. This infrastructure shift is critical for bridging the OT/IT gap and enabling the robust data loops required for commercial embodied AI.

Read
IndustryProductFeaturedRobotics Business Review

NEURA Robotics Bets $1.4 Billion Series C on Global 'Gym' Network to Solve Physical AI Data Scarcity

NEURA Robotics is leveraging its massive $1.4 billion Series C to build a global network of 10 NEURA Gyms aimed at solving the physical AI data bottleneck. By partnering with elite institutions like RWTH Aachen, the company is blending high-fidelity simulation with real-world multimodal data collection to feed its Neuraverse cloud platform and de-risk industrial deployment.

Read
IndustryProductRobotics Business Review

AMD Pushes Unified Memory and Real-Time Control into Robotics with Ryzen AI Embedded X100

AMD released the Ryzen AI Embedded X100 series and Kria AI SoM to address latency and determinism gaps in physical AI workloads. The Santa Clara company bundles unified CPU-GPU-NPU memory, Linux and hypervisor optimizations, and the open-source AMD Robotics Sophie Suite as a single scalable stack for arms, AMRs and humanoids. It positions the platform as a non-locked alternative that claims three times the FP32 performance of NVIDIA Thor on select signal-processing tasks.

Read