The on-board sensors of connected autonomous vehicles (CAVs) are limited by their range and inability to see around corners or blind spots, otherwise known as non-line of sight scenarios (NLOS). These scenarios have the potential to be fatal (critical scenarios) as the sensors may detect an obstacle much later than the amount of time needed for the car to react. In such cases, mechanisms such as vehicular communication are required to extend the visibility range of the CAV. Despite there being a substantial body of work on the development of navigational and communication algorithms for such scenarios, there is no standard method for generating and selecting critical NLOS scenarios for testing these algorithms in a scenario-based simulation environment. This paper puts forward a novel method utilising a genetic algorithm for the selection of critical NLOS scenarios from the set of all possible NLOS scenarios in a particular road environment. The need to select critical scenarios is pertinent as the number of all possible driving scenarios generated is large and testing them against each other is time consuming, unnecessary and expensive. The selected critical scenarios are then validated for criticality by using a series of MATLAB based simulations.

/pdf/selecting-non-line-of-sight-critical-scenarios-for-connected-2xwt4am1.pdf

Selecting Non-Line of Sight Critical Scenarios for Connected Autonomous Vehicle Testing

The creation of robotic vehicles for agricultural purposes is a promising direction in the automotive industry. The complexity of the self-driving truck's design, work in difficult operating conditions, and a large number of measuring devices and processing subsystems determine the relevance of creating a virtual test system. These tests are part of the overall virtual commissioning process for a robotic vehicle. The article discusses a set of basic subsystems that provide virtual tests based on a model-based approach: mathematical modeling, measurement modeling, information subsystem with databases, visualization and documentation subsystem. Metrological models of measuring channels for virtual tests have been developed, allowing simulating random vehicle parameter changes. The testing process covers all the most essential components of a robotic vehicle. For example, the article presents a dynamic model of the braking system of a robotic chassis and shows the results of braking modes' virtual tests. The developed virtual test system is used to create a KAMAZ truck as part of a robotic system for agricultural vehicles.

/pdf/virtual-tests-of-robotic-vehicle-units-for-virtual-bnid3x711t.pdf

Virtual tests of robotic vehicle units for virtual commissioning

Bus transport has been an important driver of the economic growth of Mauritius for decades. In recent years, it has been facing several challenges, such as competition from the Metro Express and an inability to upgrade its services. In addition, public buses still face inefficiencies that discourage the public to travel by them. These include bus drivers tending to drive slowly on purpose or dangerously fast resulting in their schedules at bus stops being unreliable. This paper exploits advanced technologies such as artificial intelligence, Internet of Things, cloud computing and big data analytics to enhance the efficiency of bus operations and provide a better service to the public. It presents the design and implementation of a microcontroller-based system that uses real-time data from onboard camera and GPS to monitor the condition of the road and the bus speed. The system can detect whether the bus is driving too fast or purposely too slow and upload pictures as proof. A web application is also developed to process data uploaded by the system on the cloud to provide the passengers with the exact location of the buses on a map so that they can better plan their trip. 

Improving Public Transport Efficiency in Mauritius using Artificial Intelligence and Internet of Things solutions

Bus transport has been an important driver of the economic growth of Mauritius for decades. In recent years, it has been facing several challenges, such as competition from the Metro Express and an inability to upgrade its services. In addition, public buses still face inefficiencies that discourage the public to travel by them. These include bus drivers tending to drive slowly on purpose or dangerously fast resulting in their schedules at bus stops being unreliable. This paper exploits advanced technologies such as artificial intelligence, Internet of Things, cloud computing and big data analytics to enhance the efficiency of bus operations and provide a better service to the public. It presents the design and implementation of a microcontroller-based system that uses real-time data from onboard camera and GPS to monitor the condition of the road and the bus speed. The system can detect whether the bus is driving too fast or purposely too slow and upload pictures as proof. A web application is also developed to process data uploaded by the system on the cloud to provide the passengers with the exact location of the buses on a map so that they can better plan their trip.

India is yet to accept semi/fully – autonomous cars and one of the reasons, was loss of control on bad roads. For a better handling on these roads we require advanced braking and that can be done by adapting electronics into the conventional type of braking. In Recent years, the automation in braking system led us to various benefits like traction control system, anti-lock braking system etc. This research work describes and experiments the method for recognizing road surface profile and calculating braking distance. An ultra-sonic surface recognition sensor, mounted underneath the car will send a high frequency wave on to the road surface, which is received by a receiver with in the sensor, it calculates the time taken for the wave to rebound and thus calculates the distance from the point where sensor is mounted. A displacement graph will be plotted based on the output of the sensor. A relationship can be derived between the displacement plot and roughness index through which the friction coefficient can be derived in Matlab for continuous calculation throughout the distance travelled. Since it is a non-contact type of profiling, it is non-destructive. The friction coefficient values received in real-time is used to calculate optimum braking distance. This system, when installed on normal cars can also be used to create a database of road surfaces, especially in cities, which can be shared with other cars. This will help in navigation as well as making the cars more efficient.

https://iopscience.iop.org/article/10.1088/1757-899X/263/6/062034/pdf

Rohan Desai

Papers

Braking distance algorithm for autonomous cars using road surface recognition