Automobiles provide a convenient form of transportation, and the productivity has been increasing rapidly with many smart features incorporated in competition with each other automobile industries. Despite the technology improvements, the survey showed that about 1.25 million people die each year as a result of road traffic crashes according to World Health Organization (WHO) which indicates there is an increase in road accidents by 31% from 2007 to 2017. The Department of Transportation National Highway Traffic Safety Administration found that traffic accidents are mostly caused by driver’s in-capacitance in handling the vehicle due to high-speed driving, drunken driving, misperception, decision errors, and drowsiness. Over speeding has been one of the major causes of road accidents that lead to severe trauma, such as physical injury, death, and economic loss due to panic state of driver when there is a sudden obstacle nearby, which highlights the need to develop a system that can alert drivers about the collision occurrences prior to accidents.
Cars are emerging as large smart devices with advancement in emergency braking capabilities, mapping technology for autonomous driving with better fuel efficiency. Technologies like artificial intelligence and machine learning play an important role in the future of the automotive industry as cars make predictive analysis based on the data provided by various sensors for improvising driving experience. Algorithms are being designed that use data to automate vehicle in its setup, infotainment and various application-based features.
IOT is the other major technology which is influencing the vehicle automation to get into smarter way through sensor technology and wireless communications. Broadcast technologies keep car occupants connected and entertained. Besides smart and infotainment features, safety and reliability are paramount for automotive systems. There is still a need of technologies that are to be emerged in providing complete safety to the people. As a challenge to provide the solution to the issue, Automobile industries extended their work in incorporating features that provide convenient, safe, and Connected Cars with the latest digital technologies. The systems are to be designed in such a way that it not only provides safety for the high-end cars in protecting the drivers from injuries but also should alert the nearby cars and pedestrians to avoid road accidents and damage of life.
Driver Status Monitoring Systems are developed that can determine driver drowsiness based on the measures like vehicle based, behavioural and physiological. ECG and EEG are considered for the acquisition of driver’s physiological signals. Vehicle-based parameters, such as steering wheel movement, frequency of change in lane position, vehicle speed, gear change, braking and pressure on the steering wheel. Image acquisition to observe behavioural changes calculating eye blink rate. Based on these measures level of driver’s incapacitation is detected and Automatic precautionary system is to be activated to alert the driver to prevent accidents. Driver panic situations are also considered as one of the cause for most of the accidents. Where the driver couldn’t react immediately by controlling the vehicle with sudden braking due to over-speeding which results in accidents. In such scenarios where the human fail to control, the intelligence of the vehicle will come into action.
Advances in Intelligent Transportation Systems (ITS), tend to influence this scenario in a positive manner, making it safer with massive investment for introducing ‘intelligence’ in vehicle technologies and turn them into autonomous vehicles which can cause a reduction in traffic accidents due to the mitigation of human driver errors.However, autonomous vehicles should be able to mitigate the existing hazards at the road transportation systems without creating new hazards. Thus, some critical aspects need to be better considered, such as how to ensure safety in this new vehicle paradigm. Autonomous vehicles are originated from the advancement of robotics, sensing, embedded systems, machine perception and navigation. As a result, high-end sensors, cameras, and radar have been developed and are being applied to monitor the vehicle and the environment around it, as well as requesting the vehicle or the driver to take actions depending on the situation (in some cases, hazardous situations). Technologies like park assistance and longitudinal control/guidance are part of the necessary technology to support the autonomous vehicle operation. Thus, these vehicles are gradually becoming capable to perform the same actions that human drivers have always executed. In other words, autonomous vehicles systems are capable of not only properly guiding the vehicle (for example, defining routes, acceleration, braking points, and even the acceleration for overtaking), but also controlling possible problems related to the vehicle stability.
There is much speculation concerning autonomous vehicle impacts over the currently roadway transportation system dynamics. It is believed that self-driving vehicles can extend the mobility-on-demand systems, enabling themselves to travel automatically between locations of high demand, which would help address issues such as congestion, space use, pollution, and even energy use. Due to the substantial benefits that autonomous vehicles should provide, their development has been attracting the interest of many stakeholders, mainly the automotive industry. There is already concern about how to ensure safety in those systems – like the RTS, in which there is interaction among vehicles, drivers, roadway, and environment (surroundings like obstacles and pedestrians). They must be prepared to identify the state of the elements belonging to the most critical situations so that, when they are in such situations, they need to act accordingly and be capable of reaching the safe failure state. In other words, autonomous vehicles must be prepared for unexpected, abnormal situations.
In a fully autonomous vehicle, we understand that the driver element who monitors the vehicle and the environment and has the mission of controlling the vehicle continues to exist. Consequently, its relationship with the vehicle and the environment is maintained. But, in this case, this driver element will be a machine and the relationship among RTS elements could be maintained regardless of the vehicle automation level, and the elements main missions/functionalities remain the same, the Autonomous Vehicle Control (AVC) module that will execute the driver functionalities in emergency situations. In this paper, AVC module is composed by a two-layer hierarchical architecture, with the lowest layer being responsible for protecting the vehicle movement and controlling it in critical situations where driver fail to handle the vehicle.
Vehicle to Vehicle communication also plays an important role in alerting the nearby vehicles about the abnormal condition (like rash driving, sudden braking, accident etc.) detected with a particular vehicle. The advent of IOT where every day “things” are connected together through the internet is expected to impact society and improve quality of life.
One of the applications of IOT is the vehicle fleet management systems. In vehicle fleet management systems, vehicles are able to communicate with one another and to a control centre. IOT devices are used to track location of vehicles, prevent theft or accidents, monitor vehicle activity, and report management data to a vehicle’s dashboard and wirelessly to a control centre. Current vehicle systems, which are loaded with sensing devices, require support for data transmission (in addition to voice) between vehicles and to the control centres. ZigBee, XBee S2 Pro IOT nodes and others IOT devices can be used to establish device-to-device communication network on the vehicles where there is no cellular coverage at a point in time. The device in a vehicle can act as router to another vehicle.
Researchers have attempted to develop driver status monitoring (DSM) systems based on different measures considering different parameters. Methods adopted till date to find the drowsiness state of driver are based on Facial Detection, ECG and EEG sensing based systems and eye blink rate monitoring. Present systems use some following measures to provide safety to the driver after the collision such as Air Bag inflation and Anti lock Braking Systems. The works related to the model includes following implementations till date. position, vehicle speed, change in gear, application of brake and pressure on the accelerator .This is mainly a non-contact implementation which causes less inconvenience to the driver but the conclusions drawn from the results may not be apt as the driving behaviour may be intentionally varied by the driver. Researchers have attempted to develop driver status monitoring (DSM) systems based on different measures considering different parameters.
Methods adopted till date to find the drowsiness state of driver are based on Facial Detection through image processing, ECG and EEG sensing based systems to analyse brain functioning and eye blink rate monitoring. Present systems use some following measures to provide safety to the driver after the collision such as Air Bag inflation and Anti-lock Braking Systems. The works related to the model includes following implementations till date.
Rodney Petrus Balandong designed Driver status monitoring systems include Vehicle-based estimators which consider steering wheel deviation from the lane position, vehicle speed, change in gear, application of brake and pressure on the accelerator. This is mainly a non-contact implementation which causes less inconvenience to the driver but the conclusions drawn from the results may not be apt as the driving behaviour may be intentionally varied by the driver. M.K.Alam et.Al proposed Various network topologies of sensors are connected on the scalp of human to monitor different physiological measures of the driver. Since the system includes wearable sensors which are always in connective with the person for obtaining the values, it may cause discomfort to the person and apart from that, there is huge amount of data from the sensors that is to be transferred and analysed which may need ubiquitous computing.
Abhirup Das et.Al implemented a system that monitors the driver behavioural measures that include eye blinking rate and detect any accident causing scenarios mainly during night .In case of accident, the driver’s location can be sent through a message to nearby police station.
All the proposed DSM systems till date are focused only on one of the four measures as mentioned above which lead to inefficiency in the results and based on the statistics of road accidents, drunk and driving cases are seen very often where the system fails to detect alcohol consumed driver and allows start of vehicle, which in turn fail to provide appropriate safety to the driver in accident prevention. Therefore, to increase the efficiency in monitoring the status of driver, an energy efficient system should be designed such that it considers physiological, vehicle based and behavioural measures as per the requirement and operate vehicle accordingly in safe mode preventing accidents by alerting the nearby vehicles.
This essay has been submitted by a student. This is not an example of the work written by our professional essay writers. You can order our professional work here.