The car has been produced by the research team of Phenica University, which delivers power up to 100 km / day with an average speed of 20 km / h, with the battery fully charged after 7 hours.
Dr. One morning at Le Anh Son’s school began with the self-propelled car he and his colleagues built to test sensitivity and accuracy. Instead of stepping into the car, starting with the keys and moving with the steering wheel like a normal car, Mr. Son just selects the starting point and destination, press the 6-seater car “self-propelled start” button. Rolling slowly.
As the lead researcher, Drs. According to Son, the car is equipped with Level 4 autonomous features, such as 3D maps, LIDAR sensors and high-resolution GPS, machine learning technology, deep learning, according to the Association of Automotive Engineers (SAE). These features support four groups of systems, including control systems, security systems, detection systems, and intelligent control systems.
“Currently there are two countries that conduct research on self-propelled vehicles, Japan and the United States, the highest being a unique level 3, and testing 4. Vietnam makes the first self-propelled vehicle among some countries to demonstrate its ability to master . Self-propelled technology “, said Mr. Son.
With his colleagues on the idea since July last year, Drs. Son thought the product was a 90% failure because at that time there was no research on autonomous technology, as well as infrastructure (road, smart lights). Each stage starts from scratch, “Only the passion for technology is always ready”, Mr. Son said and determined that, if it fails, teams of teachers and students at least in school use the new technologies Can be done or open documents can be created. To support future research.
It took him the first three months to find teammates, adding foreign Vietnamese scientists who had a similar desire to develop autonomous technology in Vietnam. “After only a phone call and some exchange information, the brothers doing research in Japan, Russia are ready to fly home to plan together,” Dr. Son said.
In the first phase, the team created a 3D map system so that the car could determine the starting position and destination. There are many open sources for reference in the world, but only supports detection in short distances. The team had to find ways to change the algorithm to suit the country’s terrain and traffic characteristics. Depending on the locality, the system can scan in a 3D map of a 10-hectare area in just 30 minutes.
The two major elements of autonomous vehicles are autonomy and accuracy, aided by sensors and a system of recognition. The team uses LIDAR technology, a laser-emitting sensor, to help the car determine its current position, surrounding points, and measure the angle of the steering wheel. To increase the accuracy of the vehicle, Drs. Sone used additional GPS devices to detect and report reverse of the system, so that LIDAR rearranged the vehicle’s position on the map with an accuracy of less than 1 cm.
Thanks to artificial intelligence (AI) technology, autonomous vehicles can know in front of a person or object. In the process of moving, the car automatically detects lanes, scenes, pedestrians and processes quickly. Situations such as signs, pedestrian and halting conditions. Thanks to curves, cameras and laser sensors. The more data you collect, the higher the visibility of your vehicle. People’s traits, locality, and signs are processed on the self-developed group AI model.
Dr. Son shared, as a vehicle in traffic, AI requires 100% correct identification, it is difficult to fully implement a model from abroad. Therefore, the group focused on the construction of appropriate algorithms for the actual conditions of the terrain, domestic traffic signals and driver’s behavior.
He said, when the model was completed and data was pushed into the central system, the 4G network speed was not strong enough, making it difficult for the group to transfer data. “It affects the accuracy of vehicle identification”, Mr. Son said. Finding an alternative solution, the team built an internal WiFi system so that the signal is transmitted so quickly that the central unit can detect and process everything that happens in real time.
After 6 months of manufacturing and testing through testing, the group found that the car is sensitive to the object ahead, braking immediately scare off occupants. For the car to handle smarter, he and his partner calculated the relative speed between the two objects to determine the stopping distance and applied a braking force of about 10%, with the vehicle applying the brakes.
Dr. According to Son, the product has been completed and testing and improvements have been continued to reduce costs. The team plans to shorten some of the car’s sensors, but still ensure accuracy and safety by rigorously improving the algorithm. Thus, the car has the ability to reduce itself when cornering, obstacles ahead. With an average speed of 20 km / h. In the event of exceeding the permissible speed, the system will signal an alarm, the user presses the emergency stop button.
“Currently, there are no regulations or documents under the law on autonomous vehicles in traffic, so the group wants to bring products to resorts and golf courses,” he said. In addition, the group continues to conduct research to implement autonomous technology, creating many new smart products and devices.
Freelance twitter maven. Infuriatingly humble coffee aficionado. Amateur gamer. Typical beer fan. Avid music scholar. Alcohol nerd.