Team 5

Smart Cars

Done by : Yeo Suan Ping

Zaman
Hamzih
Rui hong
Jaron
What are smart cars?
 Yeo suan ping

WHAT ARE SMART CARS??

Smart automobiles, also referred to as intelligent cars, are autos with

system-driven artificial intelligence. The fundamental idea behind a smart
automobile is to relieve the driver of numerous tedious chores related to
driving, improving the experience. Supporters of this kind of technical
advancement frequently point out that the widespread adoption of intelligent
cars might contribute to making roads far safer than they are now by
relieving the driver of at least some of the decision-making process.
Yeo suan ping

Benefits
Number uno

- ENVIRONMENTALLY FRIENDLY

Smart cars often run on electricity, so they can be recharged as opposed

to utilizing gasoline like our existing petrol-powered cars. The use of
petrol/diesel vehicles results in the release of greenhouse gases such as
carbon monoxide, nitrogen oxides, particulate matter, and unburned
hydrocarbons, all of which are finite natural resources.
Yeo suan
ping
Benefits
Number Dos
- IMPROVE TRAFFIC FLOW
Because of the capabilities of smart cars, which
include aided driving and parking, the number of
bad drivers will be considerably decreased to
virtually zero, improving the whole experience
when travelling from one place to another. As a
result, the overall flow of traffic will be improved.
There will no longer be any irregulars that could
slow down the process of reaching your
destination. For instance, lane-hoggers and those
who miraculously obtained driving privileges
despite the fact that they pose a risk of collision
everywhere they go
 Yeo suan ping

Benefits
Number tres
- SAFETY!!!!!!!!!!!!!!!!

As we all know, a certain wise man said “ Safety is number one priority”
and with that, smart cars over the years have become extremely safe with
their added features and abilities. E.g, Lane control, ABS ( Anti-lock braking
system) and emergency stop. All these features could eliminate accidents
caused by human error.
Darish

Challenges
 Challenges
What are some challenges faced by smart cars?

● RECHARGING
● BREAKDOWN
● SMALL SIZE

Darish
 Challenges
RECHARGING:

When travelling for a holiday/ long distance holiday every car that we drive needs to
be filled with petrol and we can find petrol stations to fill the car up. But due to
smart cars being electric powered, it needs to be charged and that can be a problem
as it is hard to find a rechargeable place for the smart cars.

Darish
 Darish
Challenges
BREAKDOWN:

● After travelling for a long period of time vehicles tend to breakdown or cause
problems and when that occur normal vehicles we can be able to troubleshoot
what problems is the car having but due to smart vehicles being advance and
more electronics that play apart. Therefore it is hard to fix the problem.
 Challenges
Small Size:

The small size of a smart car can, unfortunately, occasionally be a drawback. First of
all, there is no room for more than 1 passenger. These type of vehicles aren’t made
for
transporting many passengers. In addition, if you are to go shopping, you will need to
take the limited room space into account when getting a electrical smart car.

Darish
 Rui Hong

Technologies driving the smart application

- FSD Chip

Build AI inference processors that maximize silicon performance per watt while accounting for every single minor architectural and micro-
architectural improvement in order to support the Full Self-Driving software. Examine the time, power, and floor planning of the design.
Create trustworthy tests and scoreboards for the verification of functionality and performance. Utilize drivers for programming and
communication with the microprocessor that emphasize performance optimization and redundancy. When the silicon chip has been
validated, it will be put mass production for the cars.

- Dojo Chip
To fuel the Dojo technology, they have created a few different AI training chips. Every granularity of design and architecture should aim for
maximum performance, throughput, and bandwidth. Declare the chip's physical methodology, floor design, and other physical details. To
verify the functional validity, there is also pre- and post-silicon validation procedures. Write drivers and compilers to enhance the power and
efficiency of the neural networks across the entire Dojo system.
 Rui Hong

Technologies driving the smart application

- Dojo Systems
Design and build the Dojo system, from the silicon firmware interfaces to the high-level software APIs meant to control it. Solve hard problems
with state-of-the-art technology for high-power delivery and cooling, and write control loops and monitoring software that scales. Work with
every aspect of system design where the limit is only your imagination, employing the full prowess of our mechanical, thermal and electrical
engineering teams to create the next-generation of machine learning compute for use in Tesla datacenters. Collaborate with Tesla fleet
learning to deploy training workloads using our massive datasets, and design a public facing API that will bring Dojo to the masses.

- Neural Networks
Apply cutting-edge research to train deep neural networks on problems ranging from perception to control. Our per-camera networks analyze
raw images to perform semantic segmentation, object detection and monocular depth estimation. Our birds-eye-view networks take video
from all cameras to output the road layout, static infrastructure and 3D objects directly in the top-down view. Our networks learn from the most
complicated and diverse scenarios in the world, iteratively sourced from our fleet of millions of vehicles in real time.
 Rui Hong

Technologies driving the smart application

- Autonomy Algorithms
Develop the core algorithms that drive the car by creating a high-fidelity representation of the world and planning
trajectories in that space. In order to train the neural networks to predict such representations, algorithmically create
accurate and large-scale ground truth data by combining information from the car's sensors across space and time. Use
state-of-the-art techniques to build a robust planning and decision-making system that operates in complicated real-
world situations under uncertainty. Evaluate your algorithms at the scale of the entire Tesla fleet.
- Evaluation Infrastructure
Build open- and closed-loop, hardware-in-the-loop evaluation tools and infrastructure at scale, to accelerate the pace of
innovation, track performance improvements and prevent regressions. Leverage anonymized characteristic clips from
our fleet and integrate them into large suites of test cases. Write code simulating our real-world environment, producing
highly realistic graphics and other sensor data that feed our Autopilot software for live debugging or automated testing
 Hamzih
IIoT Architecture (Apps)
A connected vehicle can perform a variety of tasks while
also making driving simple for novices. It also warns you
about traffic and assists you in finding a safe route.

Some automotive industries are developing amazing

apps for automatic car parking in a tight spot or a narrow
garage.
 IIoT Architecture (Security) Hamzih

A smart car owner can keep an eye on their

smart cars even from remote locations by using
vehicular telematics.

Car owners can be assured of their vehicle's

security, surveillance, and safety at all times by
using a smartphone-enabled dashboard.
External sensors and cameras monitor the
condition of the vehicle and send data to a
mobile application. If someone tries to
forcefully enter the vehicle without proper
access, the telematics and real-time alert
system sounds an alarm on the owner's
smartphone.
 Hamzih
IIoT Architecture (Sensors)
This is a system that, through the Internet of Things and sensor
technology, provides real-time data on parking availability, both outside
and inside, as well as traffic and road conditions.
 System Design Considerations
❏ The car uses cameras, radar, and GPS antennae, along with lidar
and cameras, to detect its surroundings and identify its location.
A smart vehicle can see where it is going by using a mix of these
components to map out the road in front of it digitally.

Design considerations for lidar

➔ Thermal challenges involved

➔ Surrounding temperature and air flow
➔ Cooling mechanisms

Thermal simulation and analysis are used to identify thermal

issues before to and concurrently with electrical and mechanical
designing, ensuring that designs meet safety criteria. As a result,
the total design process is sped up, and product design is
strengthened.

Jaron
 System Design Considerations
❏ There is a growing need for DC power, which can't be met by
standard 12V DC systems, as electric cars in their different
forms replace mechanical and hydraulic systems.

High-Voltage Powertrains

➔ Delivers greater efficiencies

➔ Reduced charging time

Interconnects need higher levels of isolation to provide optimal

safety in the high-voltage environment of an electric powertrain.
Strong connections that can withstand a range of heat, moisture,
and vibration conditions are also necessary due to the
demanding operating environment of a vehicle's engine.

Jaron
 System Design Considerations
❏ The number of ADAS cameras inside and outside of vehicles is
growing as they progress toward higher levels of autonomy;
some automobile models now have 10 to 12.

High-Performing Cameras

➔ High-speed data transfer

➔ Low latency
➔ Operate under harsh conditions

Molex camera cable assemblies have bandwidths between 3 and

6 GHz and have features that ensure a strong connection, such
as retention force capabilities to endure 110 N, to meet these
high data rate needs. Molex connections for PCIe Gen 4 enable
data rates up to 20 Gbps providing more than enough bandwidth
to meet the needs of in-vehicle networking.

Jaron
End of our Presentation!