Speedy robots, a new way of identifying individuals and a few healthcare startups

May 14

Now that we have developed robots with a wide range of capabilities, how can we make them move faster? We will look at speeding up soft robots by observing and mimicking nature. We also discover a new way of identifying individuals when they …. just read the story. Finally we look at 3 Healthcare startups that I heard present this week. All 3 are making great progress.

Speeding up robots

We have all seen the videos of robots completing a wide range of tasks. Dog like robots delivering packages, robots moving through factories and the Boston Dynamics robot doing back flips. These are all Hard Robots constructed from rigid materials.

There is another type of robot called a Soft Robot. These robots are more flexible and have a different range of capabilities. Soft Robots are crawlers, that is, they always stay in contact with the ground. This limits the speed that they can move.

Inspired by the biomechanics of cheetahs, researchers have developed a new type of soft robot that is capable of moving quickly on solid surfaces or in water. These soft robots are also capable of grabbing objects with sufficient strength to lift heavy objects in addition to being able to handle delicate objects.

Previously the fastest soft robots could move was at 0.8 body lengths per second on flat solid surfaces. These new soft robots can reach speeds of 2.7 body lengths per second and can run up steep inclines (a difficult task for soft robots as they exert less force on the ground). Applications include search and rescue and industrial settings where robots can move more quickly but still handle delicate objects.

An new way of identifying individuals

We have previously spoken about the ever growing ways that facial recognition is entering our lives. From payment systems to policing. Our privacy is diminishing. Researchers at Stanford University have developed a new way of identifying individuals that now gives us zero privacy in the smallest room in the house.

It is an AI that can identify individuals by looking at their butthole. The system uses the unique features of your anoderm (I will let you look that medical term up) to identify each user. The system also uses a Pressure sensor, Motion sensor, Urinalysis strip and 4 cameras (one each for the stool and anus and 2 for urine flow) to gather information. The system also has fingerprint scanning capabilities.

Why would anyone want to do this? There is a lot of information in the excretions from the human body that will allow early detection of many health problems and diseases. For example, a couple of years ago I was part of a clinical trial in Japan for a process that used Nematodes to detect cancer in urine. It had been discovered that Nematodes were attracted to cancer byproducts that were present in human urine. A drop of urine was placed in a petrie dish with a number of Nematodes. If the Nematodes swam towards the urine it indicated the presence of cancer. It has 96% accuracy for stage 0 and 1 tumors for 15 types of cancer. It is simple, cheap and quick way to mass screen for cancer and to aid very early detection. Early detection allows less invasive interventions and a higher rate of survival. The test was released commercially in Japan on 1 January this year.

The goal of the Japanese researchers is to have a toilet that could automatically test for cancer using this approach. This toilet developed by Stanford is a first step in developing a similar type of early detection system. Information can be individualized, collected, collated and analysed and then sent off to your physician for recommendations and action.

Swoop Aero

Swoop Aero is a Melbourne based startup co-founded by a former Air Force Fighter Pilot and a Mechatronics Engineer. They have developed a Vertical Take Off and Landing drone for the delivery of urgent medical supplies. Initially they were asked if they could help transport chemotherapy medication in regional Australia.

They took up the challenge and designed a system to deliver essential medical supplies by air, safely, reliably and cost effectively every day of the week anywhere in the world that they could fly. They have since deployed aircraft in Vanuatu, Malawi, Mozambique and the Democratic Republic of the Congo. The team is based in Melbourne however their pilots control their drones, anywhere in the world they flew, from the Central Coast of NSW.

The VTOL’s are designed and 3D printed in Melbourne. Each drone can adapted to individual project and customer needs. Their system is an end-to-end aeromedical logistics management and delivery system that is transforming health supply chains around the world.

Healthmatch

Healthmatch is an Australian clinical trial matching platform that helps patients and volunteers be matched up with clinical trials for new and promising drugs and treatments. One of the difficulties in conducting clinical trials is identifying suitable volunteers.

Willing individuals sign up to the system (free of charge) and complete a medical profile. As new clinical trials are established the system searches for potential matches. Once a match has been found, individuals are notified and they have the choice to apply to join a specific trial. Once accepted, the individual is put in touch with the trial group.

The advantage for researchers is that all of the potential patients are willing trial participants and have been prescreened against the trial protocols. This saves a large amount of time and cost. Filling trials has been reduced from months to minutes. They are actively searching for Covid-19 volunteers now (both confirmed positive cases and healthy patients, see their website if interested).

Healthmatch was founded by Maguri Gunawardena, a medical student that found the traditional system for identifying potential patients for trials cumbersome, time consuming and expensive.

Tellus

Tellus is a US Healthcare startup that has offices in San Francisco and Tokyo. They have developed a radar enabled system, powered by AI, that remotely monitors the health status of someone in a specified room, e.g. an elderly person in a care home. The palm sized device can be attached to a wall from where it can measure, with precision, a person’s heart rate, breathing and movement. The device can tell if a person is walking, falling or sleeping.

These capabilities allow healthcare professionals or relatives to care for a senior person in a dignified and efficient way. The system is non intrusive and works 24/7. The device can understand if a fall has happened in the room or if someone’s movements are improving or declining.

Over time the device’s learning algorithms create a rich profile of each individual that can be used by caregivers to monitor and predict the health of those in their charge. Data collected includes Fall detection, wake up detection, sleep hours and stage of sleep, in bed hours, heart and breathing rate, in room hours, walking in the room and visitors. Centralized monitoring also allows for rapid response in times of need via emergency notifications and other alerts.

Paying it Forward

If you have a start-up or know of a start-up that has a product ready for market please let me know. I would be happy to have a look and feature the startup in this newsletter. Also if any startups need introductions please get in touch and I will help where I can.

If you have any questions or comments please email me via my website craigcarlyon.com or comment below. 

I would also appreciate it if you could forward this newsletter to anyone that you think might be interested.