A Toronto-based startup, Waabi, plans to release the Waabi Driver, a generative artificial intelligence (AI) autonomous vehicle solution to revolutionize long-haul trucking. This onboard technology uses a generative AI model to gather and analyze vehicle sensor data and make predictive decisions in real-time. Unlike current platforms from other vendors, the Waabi Driver is being empowered to think and work in human terms enabled by a simulator called Waabi World. Thus the Waabi Driver can handle endless new road conditions like a human driver. How good is this technology? Big-name investors like Uber, Khosla Ventures, Porsche Automobil Holding SE, and Volvo Group Venture Capital have been putting money into the company with Waabi’s Level-4 trucks expected to begin rolling out in Texas on the high-traffic, commercial Interstate 45 corridor between Dallas and Houston beginning in 2025.
Waabi Driver combines two generative AI models to improve road safety and accuracy. It is about creating an AI that thinks and learns like a human. Waabi Driver’s advanced generative AI simulator, Waabi World is the teacher for Waabi Driver trucks outfitted with radar, cameras, lidar and many other sensors. Compared to Waymo, Argo AI, Google and Tesla technology, the Waabi autonomous truck solution involves far less human intervention and testing.
Waabi World builds a digital twin of the real world automatically and at scale. It is unlike traditional simulators because AI is used to construct the geometry, appearance and material properties of real-world objects at scale and with the diversity and realism of the actual world. Using this digital world it creates scenarios to train Waabi Driver to reason like a human and learn from mistakes.
Waabi World’s simulation allows Waabi Driver to perform near real-time, high-fidelity sensor-based virtual simulations that mirror real-world perception. Its algorithms set Waabi Driver apart from attempts to build standard autonomous technologies as previously described on this blog site.
“The Waabi Driver has the remarkable ability to generalize,” states Waabi founder and CEO, Raquel Urtasun. “So rather than trying to train a system on every single possible data point that has ever or could ever exist, the system can learn from a few examples and handle the unknown in a safe manner.”
Waabi has combined deep learning, probabilistic inference, and complex optimization to give its autonomous systems complex reasoning, an ability to apply learned skills to unseen scenarios and geographies, and the means to interpret, validate and verify its decisions. Urtisan notes that autonomous systems like Google and Tesla use machine learning and countless rule-based examples to try and cover all circumstances, objects, road conditions and weather. That means having to train for every contingency.
The Waabi World digital twin is Waabi’s game-changer altering the autonomous driving paradigm. With its ability to create common, unpredictable and critical scenarios, Waabi Driver can use its complex AI decision-making skills to learn and rapidly adapt. When a Waabi Driver faces a previously unknown situation it understands the potential impact of its actions and can make correct responses. It thinks about the maneuvers and outcomes in real time and chooses the correct actions.
In a Fortune Magazine interview, an unnamed Waabi spokesperson describes what sets Waabi apart from any other autonomous driving system.
“The best way I can describe it is to think about a car with a tree tied to the top of its roof. Other autonomous vehicles will see this as a tree in the middle of the road and try to avoid it while Waabi’s technology allows for its vehicles to interpret the situation and realize that the tree isn’t in the road, but in fact, on top of another car, and the truck can proceed as normal.”
Urtusan describes the “exceptional ability to generalize” as the key differentiator of the Waabi ecosystem. “It’s very flexible, and it’s very fast to develop and it’s something that we can expand to do much more than trucking in the future. This could be robotaxis. This could be humanoids or warehouse robotics. This technology can solve any of those use cases.”
For now, however, the Waabi Driver is to be installed in long-haul trucks to answer the needs of an industry that is short of personnel. The U.S. needs to find 80,000 truck drivers to meet current demand and this number is expected to increase to 160,000 by 2030. The reasons for the trucker shortage are multifaceted. One of the keys is the high annual staff turnover rate of 97%.
Once the Waabi Driver rolls out, however, the demand for new drivers will lessen, and long-haul trucking will increasingly become autonomous. Investors agree with the company recently closing a US $200 million round, a testament to the technology’s recognized potential.
Where other autonomous truck companies like Embark Trucks and TuSimple have shut down operations, and Waymo recently ended its self-driving truck program, the Waabi ecosystem is not only seen as providing the missing answers but also as a less expensive solution which Urtusan says will “enable faster, safer and more scalable deployment of this transformative technology around the world.” After Waabi Driver gets rolling in Texas, plans will be put in motion to expand into other parts of the U.S. and Canada.
]]>Smart bandages with ultra-tiny biosensors that monitor wounds to help heal them faster are being developed by researchers at the California Institute of Technology (Caltech). They will soon be joining smart antibiotics in modernizing our arsenal of tools to help fight diseases and heal.
The bandages are made using a flexible polymer that contains an electronic circuit board, as well as a reusable patch with embedded biosensors, electrodes, and medications. The bandage can monitor a wound site and send information to wireless devices, release personalized medication, or emit low-level electrical fields to aid in healing. Smart bandages have the potential to treat chronic wounds like diabetic ulcers that are slow to heal and at high risk of infection.
Smart bandages feature biosensors that provide insight into how well a wound is healing. The biosensors monitor temperature, pH, and levels of lactate, ammonium, glucose, and uric acid. These metrics can indicate signs of inflammation and infection, as well as the stage of wound healing.
“Biochemical signals open up new opportunities because you’re able to really probe what’s happening on a molecular level,” comments biomedical researcher and engineer Yuanwen Jiang, now at the University of Pennsylvania. “That’s the key novelty here.” The bandage then transmits this data to a wireless device like a smartphone, tablet, or computer for the patient or the doctor to see.
Smart bandages can treat a wound site with drug-infused hydrogels. When stimulated by an electrode, these anti-inflammatory and antimicrobial hydrogels get released into the wound site. A second electrode can also apply a low-level electrical field to the site. Electrical stimulation has previously been proven to assist in wound closures as it encourages tissue growth, prevents inflammation, oxygenates, and promotes overall faster healing. “All the signals can be wirelessly sent to a user interface [such as] a computer or a cellphone,” explains Dr. Wei Goa, an assistant professor of medical engineering at Caltech. “We can wirelessly control the drug release by applying electrical potential.”
Approximately 6.5 million people in the United States have to deal with chronic wounds. these are wounds that either won’t heal, heal slowly, or heal and recur. Take diabetes as an example. Around 15 to 20% of diabetics are likely to sustain a chronic wound as high blood sugars narrow the blood vessels hampering, circulation and preventing healing blood cells from reaching wound sites. It isn’t easy to find chronic wound data. A Canadian source estimates the prevalence of diabetic foot ulcers in 75 people per 100,000 representing 60% of diabetics in the country. Extrapolating that number to the U.S. with its estimated 34 million diabetics, it translates to more than 20 million who suffer from foot ulcers that are slow healing.
Diabetics generally are at higher risk for health problems and medical emergencies with visits to hospital emergency rooms (ERs) having risen over 25% in the last decade. Controlling blood sugar levels is key to reducing diabetic risks. Medical ID tags can help identify diabetics when communicating vital health information to medics becomes difficult such as in cases where the wearer is unable to speak. Visit rates by adults with diabetes to ERs in 2020 and 2021 in the U.S. represented 72.2 per 1,000. That rate continues to rise as the population ages.
In animal studies, the smart bandages are being used for one to two weeks before changing with an estimated cost per bandage of U.S. $12. The Caltech team has treated mice and rats with diabetes and found that the bandages successfully monitor temperature, pH, and glucose levels at the wound site, and also aid in the healing process. Mice with smart bandages have healed faster and experienced less scarring than mice with unbandaged wounds.
Human studies should begin this year. The Caltech researchers also expect the results from these studies to be positive. Smart bandages may even be rolled out in clinics and hospitals within the next five to ten years, according to Dr. Gao.
]]>Tarina loves doing research and writing on a variety of topics. She prides herself in making complex concepts easy to understand. When not writing, you’ll probably find her enjoying the warm weather and taking long walks. And here in the Northern Hemisphere, the warm weather is coming.
An estimated 42% of polled respondents in a recent study by McKinsey & Company perceive charger availability as a problem should they choose to switch to an electric vehicle (EV). The same number of people also express concern about battery range. EVs account for 15-20% of global annual sales in the most recent statistics produced by the International Energy Agency (IEA). But battery issues and infrastructure are seen as impediments to even higher rates of adoption. The good news, however, is the constant improvements in battery technology is relieving range anxiety, improving charging speed, and reducing upfront EV costs. And integrating technologies built into EVs are making these vehicles even more attractive to buyers.
Improvements to charging technologies should convince more people to make the switch to green cars. These include:
Before purchasing an EV, you should evaluate your driving needs to help you determine range requirements and then consider the charging capabilities of the vehicles you’re considering. One way to do this is to use credible ratings and review sites that rank the EV performance. These sites look at the size, price, and features of EVs in the market. You should see information like how fast certain models recharge. Most EVs on standard chargers can take hours to recharge. Compared to internal combustion engine (ICE) vehicles using gasoline or diesel which usually involves a two-minute stop at the gas pump, this is clearly an EV disadvantage.
That’s why the introduction of ultra-fast chargers is so important. They significantly reduce recharging time compared to standard chargers, an important factor when travelling a long distance where drivers need to quickly juice up their vehicles to continue on their way.
Nowadays, a 150-kilowatt rapid charging station can recharge an EV in 30 minutes or less. A 350-kilowatt ultra-rapid EV charger can reach 80% in 20 minutes. Faster charging speeds minimize wait times. An EV driver that is running multiple errands with frequent stops, may choose to top up their battery if EV charging stations are readily available. This is one way to address range anxiety but it can be inconvenient. That’s why an ultra-fast charging network is highly desirable. If you are looking for the fastest EV chargers on the market today include Lucid Air (350-Kilowatt) which can top up an EV in 15 minutes and the Tesla Supercharger (250-Kilowatt) which can do it in 20 minutes.
Also known as inductive charging, wireless charging for EVs works the same way as using a charging pad for a smartphone. Wireless charging pads embedded in a parking space can be connected to a power source. When the EV parks on the pad, its receiver coils align with the transmitter to transfer the charge. Charging efficiency varies depending on several factors such as alignment accuracy and efficiency of the charging system. The advantage of wireless charging is that it offers a user-friendly charging experience because there is no need to plug or unplug cables. The other attractiveness for wireless is ease of use.
Wireless charging is efficient and fast compared to charging using a plug. The majority of EV plugs provide an efficiency rating between 80 to 95%. WiTricity’s wireless charging systems reach 90 to 93%. They can also produce charging power of up to 20 Kilowatts which is a Level 2 charging speed. For clarity, the typical power output in Level 1 charging is 1 Kilowatt with the estimated charge time from empty to full between 40 to 50 hours. Level 2 ranges from 7 Kilowatts to 19 Kilowatts. Direct Current (DC) Fast Charging comes in at between 50 to 350 Kilowatts. These types of chargers are still few and far between with DC not expected to hit the marketplace anytime soon.
Beyond building a charging infrastructure to rival current gasoline and diesel pumps, EVs have capabilities that no ICE vehicle can duplicate. This is V2X integration which enables EVs to integrate into the larger environment and communicate with other vehicles, surrounding infrastructure, pedestrians and the electrical grid.
These different integrations go by their acronyms. V2V stands for vehicle-to-vehicle. V2I involves integration with surrounding infrastructure. V2P is integration with pedestrians, and V2G is integration with the grid.
V2V allows an EV to share power with another EV that is low on charge. It’s like jump-starting a dead battery using jumper cables from one ICE vehicle to another. Toyota, Nissan, Hyundai, Kia, and Volkswagen offer V2V integration with Tesla planning to have all models support this feature by 2025.
V2I allows EVs to communicate with the surrounding environment receiving real-time information on road conditions, traffic congestion, and potential hazards.
V2P is aimed at improving pedestrian safety and awareness by providing drivers with real-time information about pedestrians within the vehicle’s vicinity.
V2G allows an EV to send electricity back to the power grid to stabilize it during peak use periods and can even generate income for the EV owner. How is this done? EVs with V2G can charge during low-demand periods and release electricity back to the grid during peak periods. V2G can also allow an EV to power a home or business during power outages making the vehicle a reliable source of backup power in the event of an emergency.
]]>