Contents built on embedded systems having capability to

 

Contents
Project title. 2
2.1 Abstract 2
2.2. Literature Review.. 2
2.2.1. Types of Road Cashes. 2
2.2.1.1. Rear End Collision: 2
2.2.1.2. T-Bone/ Intersection Collision Statistics: 2
2.2.1.3. Lateral /Lane Departure/Blind Spot Collision Statistics. 3
2.2.2. Cognition based Autonomous Vehicle. 3
2.2.3. Potential Drawback. 4
2.2.6. Emotion Based Autonomous Vehicle. 4
2.3. Conclusion: 4
2.4.  Bibliography. 5
 

 

 

 

 

 

 

 

 

 

 

 

Project title

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

 

“Emotion Enabled Vehicle System to Avoid Road Collisions”

 

2.1 Abstract

Every one of us uses vehicles to reach the destination, it saves our time making things go faster, but at the same time these vehicles possess a serious threat to our lives if ever got crashed.  Road accidents have always been the major cause of deaths and the reason is human drivers are prone to errors. Humans’ response time is much greater than that of machines leaving no chance of survival in dangerous situations.

“Emotion Enabled Vehicle” (EEV) is an autonomous vehicle that is capable of sensing its environment and navigating without human input and is able to take decisions by itself. Proposed system of EEV is to design an “Emotion Enabled Vehicle” built on embedded systems having capability to drive without the need of any human driver, communication by GPS coordinates and taking decisions on probabilistic algorithm to avoid accidents and collisions.  The proposed EEV will generate fear using fuzzy logic to determine the severity of situation so that it can generate appropriate action based on the situation or potential hazard. The proposed system would be designed with autonomous brake system that would be deployed in EEV. This brake would be applied on precision factor based on GPS based intelligent algorithm working on probability of accidents and collisions.  The purpose of this research is to develop a human inspired approach into machines to make them learn from their environment as humans do making machines more efficient to take decisions reducing the response time taken by human in emergency situations.

 

2.2. Literature Review

 

2.2.1. Types of Road Cashes

There are several types of crashes such as lateral, rear end and intersection etc. Different stratagies are required for different types of crashes such as:

2.2.1.1. Rear End Collision:

“Rear end collisions alone contributed one-third of the 6 million stated crashes in the USA (Harb et al., 2007). According to (Keller et al., 2014) during some emergency situations, where the rear end crash is about to occur, an immediate action by driver is required. These actions are difficult to perform in emergency situations; to overcome this problem an assistance system can be used.

 

An efficient path planning algorithm can help in this regard. In (Sancar, 2014) to improve the collaborative adaptive cruise control (CACC) a new approached based model predictive control (MPC) has been proposed which is helpful to control the rear end crashes.

 

2.2.1.2. T-Bone/ Intersection Collision Statistics:

According to (Wegman, 2003) head-on or T-Bones collisions are the main reason of about 60% of all deadly collisions in Economic Co-operation and Development (OECD) Member countries. According to National Highway Traffic Safety Administration (NHTSA), Intersection collisions contribute overall 47% of all vehicles collisions in United States in 2010 (NHTSA, 2012).

 

In (Kim and jeong, 2000), an algorithm has been proposed which detects the possible T-Bone and rear end collision of vehicle in common road situations. This algorithm combines assessment algorithm, tracking algorithm and the data obtained from Monte Carlo simulation to detect the possibility of the collision. To detect the threat vehicle interactive multiple model particle ?ltering (IMMPF) was utilized. The proposed algorithm can distinguish between the crash and near miss cases. The algorithm was tested in three scenarios e.g. rear-end, cut in and T-bones and the results were satisfying.

 In (Chakraborty et al., 2011) it is examined that how a sudden and power action which includes yaw rotation, can reduce the chance of T-bone crash between two vehicles at an intersection. A torque vectoring (TV) technology has been utilized in this project. It is applied on rear wheels of the vehicle and it generates the yaw rotation motion of the vehicle, with the help of which a collision may be avoided.

 

2.2.1.3. Lateral /Lane Departure/Blind Spot Collision Statistics

According to (NHTSA, 2012) every year 840,000 blind spot accidents happen in USA causing 300 fatalities. According to, only in USA 5570 and 5345 people died in lateral collisions during the year of 2012 and 2013 respectively.

 

In (Uselmann et al., 2004) a blind spot collision avoidance mechanism has been presented, which helps the drivers to avoid collisions from hazards present beyond their vision. The sonar device in this system emits wave in the blind spot to detect the obstacle. To receive the reflection of the emitted wave the sonar device has the receptor. The display panel is mounted inside the vehicle where it is visible to the driver. If there is any signal of an obstacle or object present in the blind spot, it is displayed on the screen to prepare the driver for it. In this way drivers get ability to avoid blind-spot collisions.

 

In (Schwindt et al., 2015) a lane departure warning system is presented. This system uses the front sensor to check the lane location of the vehicle and tracks the vehicle coming from the opposite side. The sensors present at the sides of the vehicle take care of the vehicle moving parallel or over taking vehicles. The information from both types of sensors is then given to the IO interface. It integrates the information and forwards it to the processing unit. Where the decisions about the lane keeping and lane departure are taken, and warnings are generated accordingly.

 

These all systems were introduced to assist drivers with its semi-autonomous system but not such system has been introduced that act by itself in an autonomous way rather than assisting drivers by generating alerts. In our proposed system we are will enable machine to decide by itself on the bases of input sensors so that a timely action can be taken. Incorporating all these mechanism for different types of accidents in one system will also reduce the cost and energy consumption as we would not be required to repeat sensors and control units.

 

2.2.2. Cognition based Autonomous Vehicle

 

Autonomous vehicles developed from the basic robotic cars to much efficient and practical vision guided vehicles. (Daniel et al., 2013) presented an approach to control a real car with brain signals. To achieve this, they used a brain computer interface (BCI) which is connected to the autonomous car. The car is equipped with a variety of sensors and could be controlled by a computer. They implemented two scenarios to test the usability of the BCI for controlling their car. In the first scenario their car is completely brain controlled, using four different brain patterns for steering and throttle/brake. In a second scenario, decisions for path selection at intersections and forking’s were made using the BCI. Between these points, the remaining autonomous functions (e.g. path following and obstacle avoidance) was still active. Brain-computer interfaces posed a great opportunity to interact with highly intelligent systems such as autonomous vehicles. While relying on the car as a smart assistance system, they allowed a passenger to gain control of the very essential aspect of driving without the need to use arms or legs.

 

2.2.3. Potential Drawback

These cognitions based vehicle systems were quite efficient on their own. They can successfully sense the environment using their sensors and then can act according to the procedural algorithm fed into them initializing the required actuator to deal with the situation. Such system can work efficiently in an autonomous environment but in real word scenarios they lack social communication with other vehicles nearby as all vehicles around may not be autonomous they can be semi-autonomous or human driven vehicles.

 

2.2.6. Emotion Based Autonomous Vehicle

Incorporating emotions into agents has been reported in (Toda, 1982), a functional role played by emotions has been observed in the behaviours of humans and animals. In the development of complex social system of animal and humans, a key role of emotions has been observed (Toda, 1982). The effects of emotions in the behaviour of agents have been tested in woggles of oz-world, where happiness improves the efficiency of agent and sadness decreases the performance of agent (Bates, 1997). It has been reported in (Frjda, Swagerman, 1987) that long term goals of agents are affected by emotions.

 

2.3. Conclusion:

 From the above discussion, it can be deduced that to build more human like agents incorporating emotions with cognitive structure of agents is necessary. Thus, if we have a desire to build agents that behave like humans, we must incorporate emotions into our design. Emotions can serve as an efficient way to prioritize an agent’s multiple goals. In this way they can reduce the computational load of rational agents. So, to make system more reliable that can implement the machine to human communication we can use emotions with cognition to make our vehicle interact with other vehicles around, no mater they are autonomous or human driven. That concludes in order to make a vehicle work in real world environment cognition isn’t sufficient without emotions or without being a social agent that can behave and interact as humans but apply action on time as machines. Thus it is clear that emotions help in decision making capabilities so we can use emotions with cognition in a vehicle to reduce road crashes.

 

 

2.4.  Bibliography

 

1: Adaptive Cruise Control or ACC is a system that automatically adjust the speed of a vehicle to keep the vehicle at a safe distance from nearby vehicles.

Harb R, Radwan E, Yan X, Abdel-Aty M (2007) Light truck vehicles (LTVs) contribution to rear-end collisions. Accid Anal Prev 39(5):1026–1036.

 

Martin Keller, Carsten Hass, Alois Seewald and Torsten Bertram,. “Driving Simulator Study on an Emergency Steering Assist” . IEEE International Conference on Systems, Man, and Cybernetics October 5-8, 2014, San Diego, CA, USA

 

Feyyaz Emre Sancar, Baris Fidan, Jan P. Huissoon, Steven L. Waslander,. “MPC Based Collaborative Adaptive Cruise Control with Rear End Collision Avoidance”. 2014 IEEE Intelligent Vehicles Symposium (IV) June 8-11, 2014. Dearborn, Michigan, USA

 

Wegman, F., 2003. Fewer crashes and fewer casualties by safer roads. In: International symposium ‘Halving Road Deaths’ organized by the International Association of Traffic and Safety Sciences, Tokyo, November 28

 

 

National Highway Traffic Safety Administration, 2012. Traffic Safety Facts 2010. U.S. Department of Transportation, Washington DC.

 

Taewung Kim and Hyun-Yong Jeong,. “A Novel Algorithm for Crash Detection under General Road Scenes Using Crash Probabilities and an Interactive Multiple Model Particle Filter”. IEEE Transactions on Intelligent Transportation Systems 2000.

 

Imon Chakraborty, Panagiotis Tsiotras, and Jianbo Lu,. “Vehicle Posture Control through Aggressive Manoeuvring for Mitigation of T-bone Collisions”. 2011 50th IEEE Conference on Decision and Control and European Control Conference (CDC-ECC) Orlando, FL, USA, December 12-15, 2011

 

 

Uselmann, David J., and Linda M. Uselmann. “Sonic blind spot monitoring system.” U.S. Patent 6,727,808, issued April 27, 2004.

 

 

Enhanced Lane Departure System,. United States Patent Application Publication Schwindt et al. Patent N0.: US 2015