Lakhasly

Abstract:
This article elucidates how DARPA - (Defence Advanced Research Project Agency) have induced a significant innovation in technology for robotic cars. It also discusses the inaccuracies and obstacles faced during the various challenges.
Introduction:
The invention of autonomous cars has influenced the automobile industry in the 20th century. In today’s life, most of the people use cars as daily transportation. However, the inefficiency faced by cars can cost us thousands of lives, in millions of accidents and billions of human hours wasted in busy streets resulting in the wastage of billions of gallons of fuels. These reviews on advances in different technology can help in creation of more efficient autonomous driving vehicles, which can reduce the amount of accidents and the traffic jams, thus curing all the problems related to clogged roads. So, this can help in building more reliable, efficient and safe face of autonomous transportation
Evaluation Of The Field (Past) Technologies:
The first GRAND challenge conducted for unmanned robotic cars in 2003 to navigate 142 miles had failed within the first few miles and it proved to be that technology was not prepared.
In 2005, DARPA repeated a "GRAND Challenge" covering 132 miles through mountains and dry lake beds with "Stanley's Stanford" clamming the first.In 2007 DARPA came up with a new competition. At the end of the Urban challenge, Junior robot claimed the second place. These challenges were the milestones in the field of robotics.

Technology (Stanley Vs Junior):
Vehicle Hardware
Below we will describe the differences and the commons between both (Stanley vs. Junior) regarding the operating computed system, design &. sensors.
Computed system:
Both vehicles are operating using Linux system.
Processors:
Stanley:
Six Pentium M Blades as a processor
Junior:
Uses intel quadcore as a processor
Design:
Both vehicles are sharing similar design.
Sensors:
Both are having sensors to detect far obstruction and ensures safety.
Software architecture
is regarded as the autonomous system's key technology.
The DARPA challenge winning automobiles featured modular software systems that function in a pi peline system to transform sensor input into actuator controls.
It typically addresses three primary functional areas:
Perception:
It converts sensor data into forecasts about the surrounding world.
Making driving judgments through planning.
Control: Based on the generated commands, it actuates the vehicle's controls (throttle, steering whee ls etc).
Since the real process duration is unknown, both vehicles' software is more adaptable thanks to their
modular architecture.
The reaction time for the new sensor data, which is roughly 300 ms for both vehicles, is also decrea sed by this module.

Both the vehicles need pre-processing and fusion
in the early stage we use the pose estimation of the vehicles which helps to send the coordinates, velocity and orientation. Kalman filters are used to wheel odometry and GPS measurements. Stanley:
Pre-processing is required for the environment sensor data. This helps in creating a 3D point cloud and converting into 2D maps.
Junior: It uses 3D scan lines are obtained from laser range finer.
The localization process
involves connecting the map and the estimated INS pose of a vehicle. This is done to ensure that the autonomous car is safe to drive. In the real world, an error tolerance of around one meter is considered acceptable.
By taking into account the vertical offsets of the map, Stanley was able to determine the vehicle's lateral placement. Localization helps in aligning the map's center line with the driveable corridor, which allows the robot to maintain its focus on the road.
Although it cannot precisely identify the lanes in the range-based features, Stanley uses a pose estimation method and the infrared remission values it can get from the laser. The combination of these two methods helped minimize the errors in GPS positioning.
Path Planning
It aids in decision-making during driving, including maneuvering the vehicle along the route based on impending dangers and road mapping. It instructs the robotic automobile on where to move on the road and what to do if a threat is met. This facilitates a smart, safe, and easy journey.
Stanley:
To reduce the impact of a collision, it adopted a fundamental planning strategy in the big challenge. However, using this technique enables the car to select the closest lane edges. Junior:
The concept is the same, but the cars had the freedom to take their own route because the urban obstacle was so difficult. The drive time from the present position of the car to the
objective time was calculated using the shortest path planner.

On the other hand, sudden traffic jams preclude the use of this dynamic approach, so Junior thought of discrete choices like lane changes and U-turns to speed up the robot's response. In the instance of unstructured navigation, Junior uses an algorithm to identify the shortest path by scanning the trees. The robot quickly responds to identify the ongoing waypoints and the consequent path in parking lots.
Behaviours And Control
The behavioural module helps in foreseeing the situations that can’t be predicted based on standard deduction of data received by sensors. One such example of situation is predicting potential traffic jams
with new technologies and by doing that, future cars will be more convenient, both legally and socially.

Stages of technological development:
There are many benefits of using self-driving cars due to advances in technology:
Many years ago, some engineers tried to manufacture a self-driving car to provide comfort for drivers. Some companies launched self-driving vehicles with different technologies, such as fully or partially robotic driving, for example:
Tesla: In 2019, it launched a self-driving car that will include all of them using an autopilot system designed to assist the driver in the most stressful parts and be safer.
Google: In 2018, its self-driving cars were known to be responsible for security, safety and parking. Nissan: In 2018, it launched the cruise control and maneuvering system.

One of the most famous self-driving cars is Google, which began developing cars from 2010 and so far has not stopped developing their industry and inventing new technologies.
Google’s unmanned cars are guided by Sebastian Thrun who also did the project on “Toward robotic cars”. He explains
Google’s car contains a lot of advantages like controlling the speed , directions,stop,and go depending on the situation. It is integrated with hardware sensors, artificial intelligence and google maps to execute the driving functions. Also it has GPS and LiDAR sensor ,GPS help the driver arrived to any location he wants .and LiDAR let him know about the real environmental conditions , etc .
The software surface installed in Google’s car gives advanced notification of factors .
Future development of this field:
Parking assistant : it will lead the car for a proper parking and help the driver to take the parking perfectly.
ACC with stop and go function : it controls the stop and go movement depending on the situation. Lane keeping assist (LKA): it controls the car to stay on the lane with a specific speed .
Military applications : autonomous vehicles can be used in war for quick decision making .
Taxi service : instead of using taxi cars , we can replace it by autonomous vehicle .
In driving cars and buses, the driver must pay attention and take into account many things, so the use of autonomous vehicles will be a development and a guarantee of safety.

Social, legal and ethical impact:
Researchers decided to develop a transportation system to reduce 90% of accidents. According to EUROSTAT, after implementing intelligent systems in autonomous vehicles, the number of deaths deceased. Traffic impacts:The combination of human control and automatically driven vehicles will affect traffic and lane changes.
This could cause problems reaction and also lead to chaos due to the merging of traffic flow with unmanned vehicles. On the other hand,the autonomous vehicles will be designed to follow the law. Over the time, autonomous vehicles will be common Insha'Allah.
Economic and industrial impact:
The fuel economy of self-driving cars could be improved by avoiding the need for efficient braking and speeding. This could save the US billions of dollars. Even if only a small portion of the change in the economy is achieved, this technology could still have a significant impact.
In addition, implementing autonomous systems could reduce the fuel consumption by 25%. The graph below shows that, compared to the human-controlled vehicles, the cost of autonomous cars is lower. However, when it comes to the operation of taxis and public transportation, the latter is more expensive.
The increasing availability of autonomous vehicles could lead to more demand and car ownerships being reduced. This technology could also help the commercial transportation industry by reducing the need for buses and shuttle cars. Some of the most common features of autonomous vehicles are GPS modules, high-resolution cameras, and LIDAR.

Environmental impact:
Most of the unmanned cars are completely electric, they significantly requires less amount of energy and gas.
Smart traffic light: Autonomous intersection in traffic flow will open up new prospectus for the cities which focuses more on green space and pedestrians
Challenges, dangers and opportunities:

• Malicious Hacking: Crime or hacking can easily manipulate self - driving cars.


• Platooning risk: Even though autonomous vehicles have potential benefits in reducing congestion. * Software and hardware failure: Vehicles with complex electronic system will often have failure even with a small system failure like interference, software error etc
  The design and implementation of the complex artificial intelligence software into the autonomous vehicle is complicated as it is the decision making (brain) of the system. Since the system is based on complete artificial intelligence, the system will be affected if the present road conditions vary. The robots will not be able make decisions like human during non-ideal conditions.
  Conclusions:
  Presently, there are many systems with ACC control, autopilot, GPS, lane changing assistant and steering control system. To make a combined system with all these, technologies will tend to conceive a full autonomous system. However, the objective is to win the trust of the people to let a computer drive the vehicle. This can be only solved by several testing and researches to get assurance for the final product. Implementing autonomous vehicle will not be accepted instantly, but people will understand the benefit of the system in overtime