Claire chatted to Andrew Philippides from the University of Sussex about what we can learn from ants and bees to improve robot navigation.
Andrew Philippides is a Professor of Biorobotics at the University of Sussex, where he co-directs the Centre for Computational Neuroscience and Robotics and the be.AI Leverhulme Doctoral centre for Biomimetic Embodied AI. His research combines biological experiments with robotics, modelling, and machine learning to understand how intelligent behaviour emerges from the interaction of body and brain acting in an environment. Focussing on visual navigation, he aims to understand the navigation and learning abilities of ants and bees to develop novel AI and biorobotic algorithms.
Most mid-market healthcare operations leaders have already looked at the major platforms. Epic Cheers. Veradigm. Health Catalyst. They have seen the demos. The capabilities look right. The implementation timelines look long, the price tags look like health system budget, and the fit to their actual data environment looks questionable.
The question becomes: what do you actually build, and what do you buy?
USM Business Systems works with mid-market health systems, specialty pharmacy groups, and pharma/CRO organizations to answer exactly that question. What follows is the framework we use.
The first thing that determines your stack is your data environment, not your budget or your timeline.
If your EHR is current, your prior auth workflow is structured, and your payer data is clean and reliable, you have more platform options. If you are managing two EHR’s from an acquisition, a prior auth process that routes through fax, and payer status updates that live in coordinator inboxes, most platforms will underdeliver.
The reason is straightforward. Enterprise healthcare AI platforms are calibrated to enterprise data infrastructure. Mid-market infrastructure is almost always messier. That is not a failure of the operations team. It is a function of how mid-market healthcare organizations grow.
A platform that assumes a clean data model will give you clean outputs in the demo and noisy outputs in production. The question to ask in every vendor evaluation: what does this platform do with dirty data?
Off-the-shelf healthcare AI platforms are strong when:
For organizations where those conditions hold, a platform makes sense. The vendor handles model maintenance, the infrastructure, and the regulatory roadmap.
A custom healthcare AI agent is the right architecture when:
The tradeoff is that custom builds require an engineering partner with healthcare domain understanding. Generic AI development shops can build the software. They often miss the operational and compliance logic that determines whether the outputs are actually usable in a regulated environment.
USM uses a three-question filter with every new healthcare engagement:
First: Is the problem standard or specific? A prior authorization workload at a specialty pharmacy managing oncology patients across 15 payers is not a standard problem. A platform built for median-case prior auth will give median results.
Second: How clean is the underlying data? If significant data normalization is required before a platform can run, that cleanup cost goes into the build-vs-buy calculation. Custom agents can be built to work with imperfect, fragmented data.
Third: What is the decision speed requirement? If you need operational improvements in 8–12 weeks, a platform with a 12-month implementation is not the right answer regardless of long-term fit.
Most mid-market healthcare operations teams land in a hybrid. They buy infrastructure at the commodity layer (EHR, practice management, claims processing) and build custom at the intelligence layer: the agent that sits on top and synthesizes signals into decisions.
That is the architecture USM – one of the best ai app development companies in USA, deploys. The agent connects to existing systems via HL7, FHIR API, or structured data export. It does not require an EHR migration or a claims system replacement. It meets the data where it is and builds the visibility and decision layer on top.
Deployment timeline: 8–12 weeks from scoping to first output. ROI measurement starts at week one.
USM offers a no-cost architecture consultation for healthcare operations leaders evaluating AI options. Book a session at usmsystems.com.
[contact-form-7]
This small drone is using sonar, similar to bats’ echolocation, to navigate through a grove of trees. Image credit: Nitin Sanket.
By Nitin Sanket, Worcester Polytechnic Institute
To help small aerial robots navigate in the dark and other low-visibility environments, my colleagues and I developed an ultrasound-based perception system inspired by bat echolocation.
Current robots rely heavily on cameras or light detection and ranging, known as lidar, or both. But these sensors fail in visually challenging conditions, such as smoke, fog, dust, snow or complete darkness.
I’m a scientific engineer who develops bio-inspired microrobots. To solve this challenge, my research team looked at nature’s experts at navigating in poor visibility: bats. They thrive in dark, damp and dusty caves and can detect obstacles as thin as a human hair using echolocation while weighing as little as two paper clips. They emit sound waves and listen to weak echoes reflected from objects.
However, enabling this sensing on aerial robots is extremely challenging because propellers generate a lot of noise. It is a bit like trying to listen to your friend while a jet engine is taking off next to you.
To overcome this issue, we present two key ideas. First, a physical acoustic shield inspired by bat’s ear cartilage reduces propeller noise around the acoustic sensors, which act like the robot’s ears. Second, a neural network called Saranga recovers weak echo signals from very noisy measurements by learning patterns over time, inspired by how bats process sound.
Together, these enable the robot to estimate obstacle locations in 3D and navigate safely using milliwatt-level sensing power.
These types of drones are very useful for search and rescue, especially in confined, dynamic and dangerous environments, because they are small and inexpensive. Search-and-rescue operations often happen in environments where visibility is very poor, such as forest fires, collapsed buildings, caves or dusty outdoor conditions. In these scenarios, traditional sensors like cameras and lidar often become unreliable.
Bats do not rely only on vision and instead use echolocation to perceive the world. Ultrasound sensing doesn’t depend on lighting conditions and works in smoke, dust and darkness.
Our work shows that it is possible to bring this capability to aerial robots despite strong onboard propeller noise. Sonar boosted by noise shielding and machine learning promises to enable a new class of small, low-cost robots that can operate in environments where current systems fail.
This research can enable highly functional, autonomous, tiny aerial robots for critical humanitarian applications, such as search and rescue, combating poaching and cave exploration. AI-enabled sonar navigation could lead to safer, faster and more cost-effective robots for time-sensitive operations where human or larger helicopter access is limited. This is a step toward being able to deploy swarms of aerial robots, much like groups of bats, to explore hazardous environments and search for survivors.
Breakthroughs in mathematical modeling, neural network design and sensor characterization will enable other low-power applications for these drones, such as environmental monitoring. Our work can reduce power by 1,000 times, weight by 10 times and cost by 100 times compared to current solutions.
Most aerial navigation systems rely on cameras, depth sensors or lidar, which degrade in low visibility. Radar works in these conditions but is power-intensive for small drones. Prior work has explored ultrasound sensing mainly on ground robots, but applying it to aerial robots has been difficult due to propeller noise and weak signals.
We are working on improving flying speed, sensing range and system size. We are also exploring new bio-inspired designs and combining ultrasound with other types of sensing.
Ultimately, our goal is to build reliable, low-power aerial robots that can operate reliably in dynamic environments and enable real-world deployment in search and rescue.
The Research Brief is a short take on interesting academic work.
Nitin Sanket, Assistant Professor of Robotics Engineering, Worcester Polytechnic Institute
This article is republished from The Conversation under a Creative Commons license. Read the original article.