Millions of deaths occur from traffic accidents every year with many efforts trying to reduce the frequency and severity of these traffic accidents.  The most effective way to tackle this problem is by means of an extensive program of road safety management, in which road safety modelling plays an essential part.

The modelling process attempts to adjust a model to the crash data, the geometric and operational characteristics of the road, and the environmental conditions, incorporating the most important factors. Numerous modelling techniques have been developed to improve the representation of reality, allowing for the employment of techniques that are more appropriate to the problems.

There have been limitations to these approaches, allowing for new opportunities, such as machine learning that SANRAL is currently exploring.  This allows to improve road safety, reduce congestion and information infrastructure development.

Machine learning can be used to detect and segment objects within the camera frame.  These objects can then be classified based on pre-trained image classification.  Which ultimately allows for the detection and classification of different types of vehicles, pedestrians, different types of animals, cyclists, etc.  The possibilities are infinite, based on the data available. 

Currently, there is ample data on the above-mentioned classification types.  While this is still in the exploratory phase within South Africa, it does come with significant risk and efforts are being made to understand how to effectively use this technology, while maintaining strict compliance with legislation as it relates to the privacy of the road users.

According to experts within the industry, the SUNBURST cyber attack appears to be one of the most complex and sophisticated cyberattacks in history.  The SolarWinds-Sunburst campaign is the first major supply chain attack of its kind and represents a shift in tactics where nation-State threat actors have employed a new weapon for cyber-espionage, and the use of a supply chain attack has changed the way one needs to defend against these cyberattacks.

These types of attacks impact not only private companies but also pose a threat to individuals and their families, given that in todays highly interconnected homes, a breach of consumer electronics could result in attackers accessing smart devices like smart phones to steal information or to act as a gateway to attack business.  Unlike government networks, that store classified information on isolated networks, private organisations often have critical intellectual property (IP) on networks with access to the internet making these attacks even more dangerous.

Hackers make us of trusted software to bypass cyberdefenses, then infiltrate the organisations and steal data, destroy data, hold critical systems for ransom, orchestrate system malfunctions or simply implant malicious content through the organization to stay in control even after the initial threat appears to have passed.

Another observation has been made on the threat that they can also use social networks, such as LinkedIn, WhatsApp, Facebook, and twitter to engage and develop relationships with and then compromise corporate employees, through who they compromise the broader enterprise.

While enterprises assert security controls over corporate issued devices and place restrictions on how consumer devices access IT assets, user activity on social network platforms are not monitored and controlled in the same way making it somewhat more difficult.

There has been a forecast that social network platforms attacks are becoming more common in the years to come, particularly among most advanced actors.

The latest thing the e-commerce giant Amazon is testing is a small, autonomous six-wheel robot that is about the same size as a large cooler to get your stuff from its warehouse to you as quickly and as cheaply as possible.  This nontraditional way of delivering parcels is powered by batteries and moves at a walking pace.

A big part of the development for the delivery robot has been done in simulations, like the way organisations have been training the neural networks that are being designed to power self-driving cars. Moving at a walking pace, each delivery device can navigate around pets, pedestrians, and other objects in its path. 

Another delivery company is also in the development of a delivery robot and looks like a small refrigerator and has completed on-road tests in four cities overseas. Both companies present similar visions: A delivery van full of robots would arrive in a neighbourhood, and robots would travel the ‘last mile’ to customers doorsteps without human aid.

During a time when so many people rely on deliveries to get what they want, bringing these new delivery bots into the network increases deliver capacity. 

We are interested to see where Amazon’s testing goes next, and whether it will allow the little delivery robot to start going out on its own without human supervision.