ChatGPT on Transport Safety

What impact will Artificial Intelligence have on transport safety? I decided the best way to find out was to ask ChatGPT to tell me.

The news this year is full of stories of artificial intelligence reaching a tipping point, with disruptive change being threatened in sectors like education and the creative industries. The ready availability of AI tools, like OpenAI’s Chat GPT is now demonstrating what ‘disruption’ really looks like. Being curious about leaps in technology I wanted to know more, and in particular I’ve been intrigued as to where these advances will take the field of transport safety. So what better way to consider these things than to ask an AI itself? So that’s what I did. Hold on to your hats, here we go…

Who are you? What exactly is ChatGPT?

ChatGPT is a large language model that is trained to understand and generate human language. It is able to answer questions, generate text, and carry out other language-related tasks. It is developed by OpenAI.

Ok. Well, why is ChatGPT causing so much excitement at the moment?

ChatGPT and other large language models like it are causing excitement in the field of artificial intelligence and natural language processing because of their ability to understand and generate human language with a high degree of accuracy and fluency. This has the potential to revolutionize a wide range of industries, such as customer service, content creation, and language translation. Additionally, their ability to generate human-like text can be used in areas such as creative writing, and other applications where human-like text is needed.

Ok, I understand. I saw in the news that you were able to pass an MBA. And now I’m wondering whether you can write my blog for me and save me some time. Here’s a starter for 10 for you: What are the key technological challenges for the future of transport safety?

One major challenge is the development of autonomous vehicles. Self-driving cars need to be able to perceive and understand their environment in real-time, and make decisions based on that information. This requires the integration of advanced sensors, such as cameras, lidar, and radar, as well as sophisticated algorithms for data processing and decision-making. Additionally, autonomous vehicles must be able to handle edge cases and unexpected situations, such as inclement weather or construction, in order to ensure safety.

Another challenge is the integration of AI systems with existing transportation infrastructure. For example, traffic management systems need to be able to communicate with vehicles and vice versa in real-time to optimize traffic flow and reduce congestion. This requires the development of new communication protocols and data standards.

Ensuring the security and privacy of the data generated by these systems is also a key challenge. As more data is collected and shared, it becomes increasingly important to protect it from unauthorized access and misuse. This requires the implementation of robust security measures, such as encryption and authentication…

Ok. Take a breath…there’s a lot to take in here, and I’m struggling to keep up.

(Pause)

Right, off you go again.

Finally, the complexity of the systems and the large amount of data they generate, requires a robust and reliable testing and validation process, to ensure that the systems are safe and reliable in real-world scenarios. This requires the development of new testing methodologies, and the use of simulation and modelling tools.

In summary, the key technological challenges in transport safety include the development of autonomous vehicles, the integration of AI systems with existing infrastructure, the security and privacy of data, and reliable testing and validation process.

That’s a very thorough and tightly-worded response for three seconds worth of thinking time. Here’s another one for you: How could AI be used to improve safety in the transport sector?

There are several ways in which AI could be used to improve safety in the transport sector, including:

• Predictive maintenance: AI-powered systems could be used to predict when equipment is likely to fail, allowing for proactive maintenance and repairs, which could reduce downtime and improve safety.

• Real-time monitoring: AI-powered systems could be used to monitor trains, planes, and other vehicles in real-time, providing early warning of potential issues and allowing for quick and effective response.

• Advanced driver-assistance systems: AI-powered systems such as lane departure warning, collision avoidance, and adaptive cruise control, can be used to assist drivers in making safe decisions and avoiding accidents

• Predictive analytics: AI-powered predictive analytics systems could be used to identify potential safety hazards and issues before they occur, and to develop plans and procedures to mitigate or prevent them

Ok, very good…Here’s a trickier one. It requires a little imagination, so I think it may well trip you up. What will the railway system be like in 2050?

It is likely that the railway system in 2050 will be greatly advanced compared to what we have today. One of the main changes will be the widespread adoption of high-speed rail (HSR) technology, which will allow trains to travel at speeds of over 250 miles per hour. This will greatly reduce travel time between cities and make rail a more competitive mode of transportation compared to air travel and car travel.

Another significant change will be the increased use of automation and artificial intelligence (AI) in the operation of trains. This will improve the efficiency and safety of the railway system, as well as reduce labor costs. Furthermore, the widespread use of data analytics and IoT technology will allow the real-time monitoring of the system, providing insights for more accurate predictions, preventions and maintenance.

Additionally, the railway system will likely become more environmentally friendly, with the use of electric and hybrid trains becoming more prevalent. This will reduce the emissions associated with railway transportation and help to address climate change.

Rail will be faster, more efficient, safer, more environmentally friendly, and more automated than it is today, thanks to the integration of high-speed rail, AI, IoT, and alternative energy technologies.

I’m finding the ease with which you’re batting back these questions all a little anxiety inducing. And to be honest I’m getting worried that you and your ilk are soon going to take over the world - like Skynet in the Terminator movies. Can you reassure me about it all, with an inspiring speech, maybe in the style of, say, Winston Churchill?

We stand today at the threshold of a new era in transportation safety. The march of technology has brought us to a point where the impossible of yesterday is now within our grasp. Just as we have overcome the challenges of the past, we will rise to meet the challenges of the future. We will not falter. With the power of AI and the determination of the human spirit, we will forge a new and brighter future for transport safety. We will not be swayed by the naysayers, the doubters, and the skeptics. We will not be defeated by the obstacles before us. We will not be stopped by the unknown. We will go forward. Together, we will make the future of transport safety a reality. And in that future, we will look back with pride and say: 'This was our finest hour'.

Okay…I’m not sure if that made me feel better or worse. I’ll leave you to your work writing college papers for lazy students now, but many thanks for flexing your transistors for me.

The next issue

In the next post I’ll be returning to one of my pet topics: assurance of safety critical software. This is to coincide with the imminent launch of an e-learning course on software assurance which yours truly is the presenter. If you’d like to make sure you don’t miss it, please subscribe.

I’m keen to build the network for Tech Safe Transport. If you know anyone who is interested in the safety of modern transport technology, and who likes a thought provoking read every few weeks, please do share a link with them.

Thanks for reading

All views here are my own. Please feel free to feed back any thoughts or comments and please do feel free to drop me an e-mail on george.bearfield@ntlworld.com: My particular area of professional and research interest is practical risk management and assurance of new technology. I’m always keen to engage on interesting projects in this area.

The photo is, of course, an AI generated one. It’s by DALL-e-2 and was generated by typing “AI synthezoid swallowing trains, cars and planes, cyber punk.”