The document presents an overview of the technology and principles behind autonomous vehicles, focusing on Google's self-driving car project and its components, such as sensors (lidar, radar, GPS) and software architecture. It discusses advantages like reduced accidents and efficient highway use, as well as challenges such as data noise and testing difficulties. The conclusion highlights the need for rigorous safety standards and the limitations of current machine learning systems in ensuring reliability.

2. Presented by
Karthik.C and ajithkumar .D
CSE II YEAR

3. CONTENTS
• Abstract
• Artificial Intelligence
• Google self driving car
• Software block diagram
• Advantages
• Difficulties
• Conclusion

4. Abstract
• Embedded system  computer hardware
with software embedded in it as one of its
important component.
• Artificial intelligence intelligence exhibited by
machines rather than humans or other animals.
• Autonomous car is a vehicle that can
guide itself without human conduction. This kind
of vehicle has become a concrete reality and may
pave the way for future systems where computers
take over the art of driving.

5. Google self driving car
• Google's self driving car project was formerly led
by Sebastian Thrun , former director of the
Stanford Artificial Intelligence Laboratory and
co-inventor of Google Street View
• Waymo is an autonomous car development
company spun out of Google's parent company,
Alphabet Inc., in December 2016. It then took
over the self-driving car project which Google had
begun in 2009

7. Software block diagram of
autonomous vehicle

8. Explanation
 Each block can interact with others using inter-
process communication (IPC) or shared memory.
ROS messaging middleware is a perfect fit in this
service.
In DARPA challenge they implemented a
publish/subscribe mechanism to do these tasks. One
of the IPC library development by MIT for 2006
DARPA challenge was Lightweight Communications
and Marshalling (LCM).

9. Sensor interface
 As the name of the module indicates, all the
communication between the sensors and the vehicle is
done in this block.
 The block enables us to provide the various kinds of
sensor data to all other blocks.
 The main sensors include LIDAR, camera, radar,
GPS, IMU, and wheel encoders.

10. LIDAR IMAGE

11. LIDAR
• LIDAR refers to a light detection and ranging
device.
• which sends millions of light pulses
per second in a well-designed pattern. With its
rotating axis.
• It is able to create a dynamic,three-
dimensional map of the environment. LIDAR is
the heart for object detection for most ofthe
existing autonomous vehicles.

12. AUTOMOTIVE RADAR

13. RADAR
 Radar is an object-detection system that uses radio waves to
determine the range, angle, or velocity of objects.
 It can be used to detect aircraft , ships , spacecraft, motor
vehicles,etc
 Radar system consists of a transmitter which is producing
electromagnetic waves in the radio or microwaves domain, a
transmitting antenna, a receiving antenna (often the same
antenna is used for transmitting and receiving) .
 A receiver and processor to determine properties of the
object(s).
 Radio waves (pulsed or continuous) from the transmitter
reflect off the object and return to the receiver, giving
information about the object's location and speed.

14. GPS
• GPS relies on triangulation, or more correctly,
trilateration to determine the receiver
position.
• By knowing the distances between the user
and some known reference points, the user’s
position can be determined using geometry.
• The reference points used by GPS are of
course the satellites.

15. • So, if we send a radio message to the receiver
with the time that the message
• was sent, the receiver can calculate the distance
by subtracting the time of transmission,
• ToT,  the time of arrival
• ToA to get the time of flight
• C Velocity of Light.
• D=C(ToA-ToT)

16. Perception
 These modules perform processing on perception
data from sensors such as
• LIDAR
• camera
• Radar
 segment the data to find moving and static objects.
 They also help localize the self-driving car relative to
the digital map of the environment.

17. i) localization
• Methods for localization:
• 1mapping and map based localization.
• 2lateral localization.
• 3visualization.

18. ii)Obstacle avoidance
• To avoid obstacles in autonomous system
different sensors are used .
these are,
• 1IR sensor.
• 2Ultrasonic sensors.

19. Block Diagram Of This Process

20. Working principle
 To The obstacle avoidance robotic vehicle uses
ultrasonic sensors for its movements.
 A microcontroller of 8051 family is used to achieve
the desired operation. The motors are connected
through motor driver IC to microcontroller.
 Whenever the robot is going on the desired path the
ultrasonic sensor transmits the ultrasonic waves
continuously from its sensor head.
 Whenever an obstacle comes ahead of it the
ultrasonic waves are reflected back from an object
and that information is passed to the microcontroller.
 The microcontroller controls the motors left, right,
back, front, based on ultrasonic signals. In order to
control the speed of each motor pulse width
modulation is used (PWM).

21. Navigation
• This module determines the behavior of the
autonomous car.
• It has motion planners and finite state
machines for different behaviors in the robot.
1path planning.
2top level control.

22. Path planning

23. Vehicle interface
 After the path planning, the control commands,
such as steering, throttle, and brake control, are
sent to the vehicle through a drive-by-wire
(DBW) interface.
DBW basically works through the CAN bus. Only
some vehicles support the DBW interface.
Examples : i) Lincoln MKZ
ii) VW Passat Wagon
iii) some models from Nissan.

24. Simulating process
• In this section, we are simulating and interfacing
some of the sensors that we are using in self-driving
cars. Here is the list of sensors that we are going to
simulate and interface with ROS:
• Velodyne LIDAR
• Laser scanner
• Camera
• Stereo camera
• GPS
• IMU
• Ultrasonic sensor
simulation using ROS and Gazebo and read the sensor.

25. Design Of Autonomous Car

26. User interface
The user interface section provides controls to
the user.
It can be a touch screen to view maps and set
the destination.
Also, there is an emergency stop button for
the user.

27. Global services
 This set of modules helps log the data and has time
stamping .
 message-passing support to keep the software
running reliably.
1vehicle health status
2data logger
3Inter process control

28. other technologies used in
Autonomous car
Anti lock brakes(ABS)
Electronic stability control(ESC)
Cruise control
Lane Departure warning system
Self parking
Automated Guided vehicle system
Automated Night Vision
Adaptive High Beam.

29. Features And sample drive

30. Advantages
• Reduction in car accident
• Optimal speed
• Increase in productivity
• Efficient use of highways
• Fuel economy
• Maximum utilization of parking space
• Reduction in car theft ,due to the vehicle’s self
awareness.

31. Limitations
1noisy data
2Incompleteness
3Dynamicity
4Discrete measurement in real time ,etc.

32. Conclusion
• Fully autonomus vehicles need ISO 26262 plus more.
• Doing enough test is challenging even worse..
• Machine learning system are inheritantly brittle and
lack legibility.
• Challenges mapping to tradition safety V model.
training data is the de fact requirement +design.
no determinism makes it difficult to do testing.
• Potential solution elements:
run time safety monitors worry about safety ,not
“correctness”.
testing philosophy should include black swan events.

33. THANK YOU ALL 