Mar 18, 2023, 10:06
A research team from Tsinghua University has made a breakthrough in autonomous driving, developing a technology that allows vehicles to self-learn while driving to deal with unfamiliar situations, an innovation that could resolve self-driving safety concerns.
Conventional self-driving technology is based on an algorithm with more data collected through lengthy training in possible driving scenarios, whereby the car has a preset response plan in case of emergency. Therefore, the car might not know how to react in unfamiliar situations in which it has not trained, posing a threat to driving safety.
The new technology enables continuous performance improvements in cars using the data collected during autonomous driving, unlike the conventional method of training cars as much as possible in various driving scenarios in advance, according to the study findings published in the journal Nature Machine Intelligence.
The research team evaluated the newly-proposed technology through both simulations and road tests, with the results showing that cars could learn in new situations and their performance was continuously improved as the driving mileage and data volume increased, said Cao Zhong, a team member from Tsinghua University.
The technology was applied in vehicles at the 2022 Beijing Winter Olympics, said Yang Diange, the team leader, noting that it will be further verified on a large scale on open roads with multiple scenarios.
source: CGTN
This news makes me recall hot topics widely discussed in recent days, which was aroused by ChatGPT. Debates such as: Is the ChatGPT a kind of leading AI technology that the current stage of AI technology in China can't prevail? Or, has China already had similar technologies as ChatGPT and where did they deployed? Given the escalating tension situation between the US and China, many worry about in case China fails to master such kind of technology, China will lose the competition with the US. Here comes the news. It shows in this article that China has a breakthrough in autonomous driving. China's are more partial to engineering aspect, driving to solve real troubles or challenges that humankind can't fulfill, while the US is good at virtual end, to realize the human-machine interaction. Both nations have their own highlights. Personally, I think the former one's direction is more meaningful in spite of the virtual end evolving to some extent can bridge the gap of increasingly spiritual hollows of human beings due to lack of interhuman communication, engineering end innovation, on the contrary, can meet the vital advancement demands of human beings, release productivity, so as to have a more comfortable life. Along this way, people like us might be easier to spare time to retrospect on the wrong doings of what we had done in the past and rethink how we can improve in the future. People who lack interhuman communication because of the heavy burden of life might become relieved and could shift more focus from work to relationship building. In return, it will also be conducive to cure the disease of a hollow spirit.
In this sense, to my view, that's the reason why I prefer to the way of the former one.
After all, despite the fact that the entire world's substances have gotten richer and more developed in the past a few decades, we still have a long way to go to lift starvation and poverty.
'' a technology that allows vehicles to self-learn while driving to deal with unfamiliar situations'' Even the most skilled drivers in China would encounter situations where other drivers are behaving erratically and so ( together with natural hazards such as fog, rain, sink holes) an accident is possible around every corner.
Community login
Add a comment