- August 25, 2022
- allix
- Research
JDN. You advocate a new proof-of-responsibility role for the IoT in asset tracking. Can you explain the concept?
The founder of the start-up Goodflow is leveraging artificial intelligence and radio technologies so that sensors can provide accountability in the event of a supply chain incident. Ronan le Roy. In Europe, each year, the use of single-use cardboard industrial packaging generates more than one billion tonnes of CO2. To divide these CO2 emissions by three, we would have to switch from disposable to reusable packaging. But today these represent only 20% of the market, the use has not yet entered into habits. The reason: too much reusable packaging is lost, broken, or stolen and it is impossible to assign responsibility for these malfunctions. And the quantity and variety of players in logistics loops are constantly growing. Consequently, it is the owner of the reusable packaging who pays. The cost of these malfunctions is several hundred million euros, especially since the owners who must guard against the risk of rupture buy four to five times more than necessary. Therefore, they consider the return on investment too weak. This does not encourage manufacturers to get started.
This is why the IoT must go beyond simple location and reliably identify the user legally responsible for each package, and from when to when. This is the only way to make the logistics loop more reliable and to assign responsibility for an accident or theft to a factory, for example. Because that’s the root of the problem: what really interests manufacturers is knowing who is responsible for their package, and who must therefore pay in the event of a problem.
How does your solution work?
It consists of a connected object whose role is to collect irrefutable information and an application that will aggregate it and deduce reasoning from it. The lifespan of the connected object is greater than that of the packaging on which it is fixed because manufacturers generally do not change the batteries but the entire IoT. Replacing tons of CO2 with electronic waste due to end-of-life IoT is not our goal. To guarantee this autonomy, our connected object does not geolocate the packaging it is in, this technology consumes far too much energy. He will look at the radio networks present and send by long-range radio the very simple elements that he will have observed. He is also able to communicate with others. connected objects. It is also able to understand the movements of the packaging.
The application in the cloud aggregates the data and deduces from it reasonings which attribute responsibilities… legally opposable. This is also a particularity of the algorithms of our application. Concretely, the owner of the packaging knows where his packaging is and since the factories rarely travel during the night, he knows where it is. If a package is broken at a specific time and at that same time it is possible to prove who was responsible for it, then it is possible to prove who is responsible for the problem. Our customers seek above all to understand the conditions under which problems arise, so as to put in place processes that make the use of their reusable packaging more reliable. As the blockchain consumes a lot of energy, we don’t want to use it, but we have a reliable solution that also guarantees the authenticity of our customers’ information.
With our solution, there is no infrastructure to install where packaging passes through, which removes a barrier for customers. The GoodFloow solution is entirely eco-designed, which means that we checked when creating our service, that the reusable packaging equipped with the connected object and its application has a much lower impact than the cardboard packaging solution. and wooden pallets. The cost of using reusable industrial packaging with the GoodFloow system and its subscription is three times cheaper than the cost of using disposable cardboard. Ademe is auditing us on this eco-design part, following the PERFECTO call for projects that we won in 2021.
What are your deployment prospects?
Goodflow is filing patents (a first was validated by the INPI, editor’s note). We are developing, with Inria in Lille, IMT Nord Europe, IMT Atlantique, and Irisa in Lannion, technological bricks that do not exist. These innovations allow us to carry out POCs of 5,000 connected objects deployed with companies that own fleets of reusable industrial packaging in the automotive and chemical sectors. The goal is to have 25,000 IoT devices installed within two years.
In the shorter term, what are your projects for the end of the year?
We want to make the solution able to adapt to any packaging in any environment, be it a metal roll, a mesh container, etc. A new R&D program will therefore be launched from 2023 to 2026. In parallel with the filing of patents, we are developing a consulting offer to help manufacturers on the subjects of adapting their supply chain to reusable industrial packaging to improve their CSR rating… We would like to launch this activity during the first quarter of 2023. The objective would be to make Goodfloow a company with a mission as soon as possible. In 2023, Goodfellow will also raise funds. The rise of CSR and carbon footprint reduction policies will encourage the development of the IoT. But for that, you have to create value differently so that technology is at the service of ecology and has a real CSR impact. Only in this way will companies switch to reusable packaging.
Ronan le Roy made his career in the automobile. Faced with the low penetration of reusable packaging in the supply chain, he decided to create his start-up in Nantes in January 2019, Goodfellow. The latter aims to automate the monitoring and management of reusable packaging in order to simplify and make the transition to an agile and sustainable supply chain more reliable.
Categories
- AI Education (39)
- AI in Business (64)
- AI Projects (87)
- Research (59)
- Uncategorized (1)
Other posts
- Platform Allows AI To Learn From Continuous Detailed Human Feedback Instead Of Relying On Large Data Sets
- Ray – A Distributed Computing Framework for Reinforcement Learning
- An Innovative Model Of Machine Learning Increases Reliability In Identifying Sources Of Fake News
- Research Investigates LLMs’ Effects on Human Creativity
- Meta’s Movie Gen Transforms Photos into Animated Videos
- DIY Projects Made Easy with EasyDIYandCrafts: Your One-Stop Crafting Hub
- Why Poor Data Destroys Computer Vision Models & How to Fix It
- Youtube Develops AI Tools For Music And Face Detection, And Creator Controls For Ai Training
- Research Shows Over-Reliance On AI When Making Life-Or-Death Decisions
- The Complete List of 28 US AI Startups to Earn Over $100 Million in 2024
Newsletter
Get regular updates on data science, artificial intelligence, machine