Hospital robotics: measles units, sensor makers and the slow surgery rollout
The robot industry's own trade press capped a busy September with a top-10 list on 1 October, while a UK evidence review found no clear overall benefit from robotic hip and knee replacement. The two stories point at the same thing: hospital robotics is spreading unevenly.

On 1 October, The Robot Report published its roundup of the ten most-read robotics stories of September 2026. The list was dominated by industrial and humanoid news rather than operating theatres. Boston Dynamics opened a Metaplant Application Center at Hyundai's Georgia plant to train Atlas. Qualcomm agreed to acquire PickNik and pledged to keep MoveIt open source. Agility unveiled Digit 5. Intrinsic open sourced parts of its platform. The only clinical item in the top ten was a humanoid for parents, priced at $3,555.
That is a useful corrective to the way hospital robotics is usually covered. The trade press that tracks the technology most closely is not currently leading with surgery.
What the evidence says about orthopaedics
Meanwhile, the evidence base for the highest-profile hospital robot category, orthopaedic joint replacement, took a hit this week. News-Medical reported on 1 October that robotic-assisted hip and knee replacements show no clear benefit over conventional methods. Medical Xpress reported the same day that robotic surgery fails to cut the overall risk of repeat surgery. MedPage Today was blunter on 30 September, calling the UK studies an "Epic Fail" for the case that robots improve joint replacement outcomes.
The nuance matters. These studies look at revision rates and broad outcomes across a population, not at surgeon-level metrics such as implant positioning or soft-tissue handling. A hospital buying a robot is buying a system, and the system's value depends on volume, training and case mix. The UK findings do not say the machines are useless. They say the population-level benefit is not established.
That reading is consistent with what the industry itself is selling. Medical Device and Diagnostic industry asked on 1 October whether compact robotics can finally convert orthopaedics' roughly 80% non-robotic surgeon market. The framing is about adoption and price, not clinical superiority.
The money is still moving
Capital keeps flowing regardless. CMR Surgical has been running a surgeon outreach and hiring push to drive adoption of its Versius Plus system, according to TipRanks on 26 September. Intuitive Surgical received a CE mark for da Vinci 5 cardiac procedures, MassDevice reported on 30 September, and Kalkine Media noted further robotic approvals on 1 October. Trinity Health expanded access to robotic aortic valve replacement, thelivingstonpost.com reported on 25 September.
Outside the US and Europe, adoption is often framed as access. Visakhapatnam's Mahatma Gandhi Hospital completed 500 robotic cancer surgeries, Dainik Jagran MP CG reported on 2 October, the same milestone picked up by another outlet the same day. Assam performed its first robotic heart surgeries at Guwahati Medical College and Hospital, according to ETV Bharat on 26 September.
Not every deployment is surgical. WIRED reported on 1 October that US measles cases have topped 3,600, the highest yearly total since 1991, and that hospitals are rebuilding infection-control protocols. The University of Pittsburgh Medical Center's community hospital in Lititz, in Lancaster County, has evaluated around 50 measles patients, roughly 20 of them requiring hospitalisation. Pennsylvania has recorded 943 cases, 176 hospitalisations and five measles-related deaths as of 30 September, WIRED reported. The hospital now screens patients by phone, has them wait in the parking lot and escorts them to negative-pressure rooms.
That is hospital adaptation driven by epidemiology, not robotics. But it shows how quickly a care pathway can be redesigned when the pressure is real, and it is the kind of operational problem that automation vendors keep promising to solve.
The unglamorous layer
Where robotics is actually advancing inside hospitals, it is often in sensing and infrastructure rather than the operating table. Vishay Precision Group will present custom force and torque sensing for humanoid robotics at RoboBusiness 2026, The Robot Report reported on 1 October. Ron Zukerman, the company's innovation director, said in that announcement that VPG focuses on "precision sensing solutions exactly where they are needed most: at the key points of performance, safety, and control in today's advanced intelligent systems."
The technical argument in that piece applies directly to surgical and assistive robots: off-the-shelf sensors are often too large for small limbs, their measurement ranges are too broad, and they need bulky external electronics. Custom strain-gauge sensors built into the structure are the alternative VPG is pitching.
Compute is moving in the same direction. Microsoft Research argued on 23 September that running physical AI inference only on onboard GPUs limits robot performance, battery life and scalability, and that offloading inference to edge or cloud GPUs improved task success rates across representative mobile manipulation workloads.
NVIDIA, meanwhile, is trying to secure the agent layer. On 28 September The Robot Report covered NVIDIA's Open Agent Safety Platform, built from the open-source OpenShell runtime and the Sentry reference design, with Gecko Robotics among more than 100 organisations working with the technology. Jensen Huang, NVIDIA's CEO, said in a statement that "safety and security require full-stack engineering." Justin Boitano, vice president of enterprise AI at NVIDIA, said during a press briefing that an independent trust domain works "like how self-driving cars work."
That analogy is the point. Surgical robots are already regulated medical devices, but the AI agents being layered on top of hospital hardware are not, and the security incidents NVIDIA cites happened entirely in software.
Europe, China and the gap
Europe's own industrial policy for robotics remains a proposal. Bruno Siciliano, professor of automation and robotics at the University of Naples Federico II, told Il Sole 24 ORE on 1 October that the EU should develop a European model of physical AI built around human interaction rather than replacement, and warned of a possible bubble. He cited BMW's rethink of its use of Figure AI humanoids at its South Carolina plant as evidence that the fully anthropomorphic version is not always productive in a factory, on grounds of cost, stability and movement in confined spaces. Siciliano said he and the euRobin network discussed an AI-based robotics act at the European Parliament in Brussels in early September, with a proposed 30 billion euro budget and a target of 33% of the world market by 2035.
Adoption inside hospitals varies just as widely by region. Accenture found that only 10% of Hong Kong firms surveyed had integrated generative AI across multiple business functions, against about 21% of mainland Chinese enterprises, the South China Morning Post reported on 29 September. Robert Hah, Hong Kong office lead at Accenture Greater China, attributed the gap to legacy systems and risk aversion. Hospitals are the archetypal legacy-system buyer.
Two smaller signals round out the picture. Barbara Mazzolai, associate director for robotics at the Italian Institute of Technology and director of its Bioinspired Soft Robotics Laboratory, told IEEE Spectrum on 22 September that sustainability robotics should treat the environment as more than inspiration, a research direction with obvious long-term relevance to implantable and assistive devices.
And on 2 October, The Robot Report opened submissions for its 2026 Robotics Startup Radar, open to startups five years or younger, with entries due Tuesday, 6 October 2026. Last year's list ran to 100 companies. The 2026 edition is sponsored by Maxon Precision Motors and PTC.
None of this resolves the central tension. Robots are entering hospitals through orthopaedics, cardiac surgery, cancer care and infection control at once, and the clinical case for each is being tested separately. The UK joint-replacement findings are a reminder that adoption curves and evidence curves do not move together.
Sources
12- 01Top 10 robotics stories of September 2026EN
- 02Vishay Precision Group to showcase custom sensing capabilities for humanoid robotics at RoboBusiness 2026EN
- 03Calling robotics startups: submissions for the 2026 Robotics Startup Radar close soonEN
- 04Gecko Robotics works with NVIDIA to add AI agent security and controlEN
- 05Measles is forcing hospitals to adapt to a new normalEN
- 06Umanoidi, il professore di robotica Bruno Siciliano: l'Ue punta sull'interazione tra uomo e macchinaEN
- 07Hong Kong firms lag mainland China on AI adoption amid legacy-system burden: AccentureEN
- 08Offloaded inference for real-world physical AI roboticsEN
- 09Barbara Mazzolai wants to build a new field of roboticsEN
- 10NVIDIA Isaac ROS 5.0 advances agentic, open source robotics developmentEN
- 11Health insurer points finger at AI as nearly $1 billion in questionable hospital charges appearEN
- 12How Maven Robotics plans to automate industrial work, one task at a timeEN
All figures and quotations in this text come from the sources listed below.
Content prepared by the editorial team with AI assistance.
Comments
0- No comments yet — be the first.