REPORT
ON
AUTOMATION VEHICLES
DEPARTMENT OFCOMPUTER SCIENCE
SUBMITTED BY:
BIKRAM CHETRI
University Enrolment No: 23FHPCNND07009
SUBMITTED TO :
AKUMLONG LONGKUMAR
HEAD OF DEPARTMENT
D e p a rt me n t o f C om pu t e r S ci en c e I c fa
iU ni ve rs i t y N ag al an d
CONTENTS
1. INTRODUCTION
2. LEVELS OF AUTOMATION
3. CHALLENGES
4. FUTURE OF AUTOMATION
INTRODUCTION
Introduction on Automated Vehicles
Automated vehicles, also known as self-driving or autonomous vehicles, represent one of
the most transformative advancements in modern transportation. These vehicles are
equipped with advanced sensors, software, and artificial intelligence systems that allow
them to navigate and operate without direct human input. Using technologies like
LiDAR, radar, cameras, GPS, and machine learning algorithms, automated vehicles can
detect their surroundings, make decisions in real-time, and safely drive on roads.
The goal of automation in vehicles is to improve road safety, reduce traffic congestion,
lower transportation costs, and provide mobility solutions for those unable to drive.
Automation in vehicles is typically categorized into levels, from Level 0 (no automation)
to Level 5 (full automation with no human intervention).
As the automotive industry rapidly evolves, companies and governments worldwide are
investing heavily in autonomous technology, aiming to create smarter, safer, and more
efficient transportation systems for the future.
Levels of Driving Automation (SAE Levels 0–5)
Level 0: No Automation
Description: The human driver is fully responsible for controlling the vehicle at all
times.
Example: Basic cars with no automated features. Some may have warning systems
(like lane departure alerts), but these do not control the car.
Level 1: Driver Assistance
Description: The vehicle can assist with either steering or acceleration/deceleration
using advanced driver assistance systems (ADAS), but not both at the same time.
Example: Adaptive cruise control OR lane-keeping assist (but not both together).
Level 2: Partial Automation
Description: The vehicle can control both steering and acceleration/deceleration
under certain conditions, but the human driver must remain engaged and monitor the
environment at all times.
Example: Tesla Autopilot, GM Super Cruise (with driver attention).
Level 3: Conditional Automation
Description: The vehicle can manage all driving tasks in certain environments or
conditions (like highway driving), but the driver must be ready to take over if the
system requests.
Example: Some advanced systems under testing, like Honda’s Level 3 system in
Japan.
Level 4: High Automation
Description: The vehicle can perform all driving functions in specific conditions or
without human input. No driver intervention is needed within those areas.
Example: Autonomous shuttle buses or taxis in controlled urban zones.
Level 5: Full Automation
Description: The vehicle is fully autonomous in all environments and conditions.
No steering wheel or pedals may be needed. No human driver required at any time.
Example: Still in development—considered the "ultimate goal" of self-driving
technology.
Challenges of Autonomous Vehicles
1. Technological Challenges
Sensor limitations: Cameras, LIDAR, and radar can struggle in extreme weather
(fog, snow, heavy rain), poor lighting, or when road markings are faded.
Complex decision-making: AVs must understand and react to unpredictable human
behaviour—like jaywalkers or aggressive drivers—which is hard to program.
Edge cases: Rare or unusual situations (e.g., a mattress falling on the road) can
confuse AI systems that haven't seen such scenarios before.
2. Legal and Regulatory Issues
Lack of clear laws: Many countries don’t yet have comprehensive regulations for
fully autonomous vehicles.
Liability concerns: Who is responsible in case of a crash—manufacturer, software
developer, or the passenger?
Standardization: Different regions may require different systems, making global
deployment more complex.
3. Ethical Dilemmas
Moral decision-making: How should an AV decide between two harmful outcomes
(e.g., hitting a pedestrian vs. swerving into a wall)?
Bias in AI: AV systems trained on limited or biased data might not perform equally
well in all communities or environments.
🚧 4. Infrastructure Readiness
Outdated roads: Poor road conditions, missing signs, and inconsistent lane
markings can confuse AV systems.
Lack of smart infrastructure: AVs benefit from connected traffic lights, smart
signs, and vehicle-to-infrastructure (V2I) communication—many areas lack this.
5. Public Trust and Acceptance
Safety concerns: Many people are hesitant to trust a machine with their life,
especially after highly publicized AV accidents.
Job displacement fears: There's concern about AVs replacing drivers in industries
like trucking, taxis, and delivery services.
6. High Development and Implementation Costs
Expensive tech: Sensors like LIDAR and high-performance computing systems are
still costly.
Scalability: Moving from prototype to mass production while maintaining safety
and performance is a huge financial and engineering challenge.
Future of Autonomous Vehicles
Levels 3 & 4 autonomy will become more common in the next few years (especially in
taxis and shuttles).
Robotaxis and autonomous delivery services will grow, led by companies like Waymo,
Cruise, and Tesla.
Self-driving trucks will transform logistics, especially for long-distance freight.
AI, sensors, and 5G tech will make AVs smarter and safer.
Smart cities will support AVs with connected infrastructure.
Benefits: Fewer accidents, lower emissions, and more mobility access.
Challenges: Regulation, public trust, job loss, and ethical dilemmas.
By 2030, AVs may be common in cities, with growing adoption in transport and
logistics.
