Self Driving Toy Robot Car Using Deep Learning
The goal of this project is to make an autonomous self-driving car, capable of guiding the car around bends, avoiding obstacles and following traffic signals and different traffic signs on the road. Machine learning model guides the car in the environment t based on the data set on which it is
2025-06-28 16:34:57 - Adil Khan
Self Driving Toy Robot Car Using Deep Learning
Project Area of Specialization RoboticsProject SummaryThe goal of this project is to make an autonomous self-driving car, capable of guiding the car around bends, avoiding obstacles and following traffic signals and different traffic signs on the road. Machine learning model guides the car in the environment t based on the data set on which it is trained. The model uses neural networks as the underlying learning framework.
Project ObjectivesThe objectives of the system are
- To avoide accidents caused due to driver faults.
- Use Raspberry Pi controller and H-Bridge drives four DC Gear motors to realize vehicle automation.
- Use ultrasonic sensors for obstacle detection.
- Image processing for traffic signs and traffic signal detection using Camera.
The deep neural network, will communicate with the car using a Raspberry Pi. The embedded software in Raspberry Pi will itself communicate with the car using an Arduino Uno. The Arduino Uno will run the car. The Raspberry Pi Camera Module connects onto the Raspberry Pi. The ultrasonic distance sensor communicates with Arduino.
The embedded software system on the Raspberry Pi has the following interfaces:
1. Camera input using a built-in library in Raspbian OS.
2. Speed and turn data output to the Arduino using RPi.GPIO library.
The embedded software system on the Arduino Uno has the following interfaces:
1. Direction and speed data input using built-in Arduino libraries.
2. PWM output to motors using built-in Arduino libraries.
Benefits of the ProjectRecent developments in machine learning and artificial intelligence along with the ever-increasing perfformance of modern day computers have enabled the use of these technologies in developing self-driving cars. These cars have several advantages, as described below:
- Better Road Safety: MAchines are not liable to human-error, leading to appropriate responses in real-time road conditions.
- Increased Productivity: Avoide accidens and increase productivity.
- Solution to Parking Problems: Most of the modern cities face parking problems and which can be resolved by this solution.
- Better Traffic Discipline: Better law enforcement can be achieved and traffic can be managed by capping speed in various regions.
- Potential for a new Design: Because a vehicle may eventually function as a self-guided train car, the potential for a new car designs is huge. With no need for complicated driving tools, self-driving cars could include new ways to relax or to stay entertained.
- Reduce Expenditure: Reduction in accidents ill directly lead to reduce expanditures on damages.
- 'Environment-Friendly: Efficient driving styes of the self-driving car will lead to lower emissions.
The car accelerates straight until a new stimulus is introduced into the environment. When encountered with a left curve car starts to turn left until a new stimulus is introduced into the environment. When encountered with a right curve car starts to turn right until a new stimulus is introduced into the environment. When the car encounters an inactive traffic signal right in front of it on the road. The car continues to move at this speed until it has passed the traffic signal, then accelerates and continues its motion with original speed, depending on the environment and the stimulus received. When the car encounters a RED traffic signal right in front of it on the road. The car stops and remains stationary until signal reverts back to green, then resumes its motion, depending on the environment and the stimulus received. When the car encounters a YELLOW signal then the car remains stationary until signal reverts back to green, then resumes its motion, depending on the environment and the stimulus received. If a GREEN Signal is encountered, the car accelerates straight until a new stimulus is introduced in the environment. Car must follow all the traffic signs according to the law. If any object appear in front of the car then car will stop and turn where car will find path.
Final Deliverable of the Project Hardware SystemCore Industry TransportationOther IndustriesCore Technology RoboticsOther TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 43100 | |||
| Raspberry pi 4 | Equipment | 1 | 16000 | 16000 |
| Chassis Car parts,motors,Arduino,H-bridge,batteries,charger,camera,etc | Equipment | 1 | 11450 | 11450 |
| wires | Equipment | 7 | 120 | 840 |
| data cable for raspberry pi | Equipment | 1 | 250 | 250 |
| servo motors | Equipment | 2 | 350 | 700 |
| Sd card | Equipment | 1 | 600 | 600 |
| Travel expenses | Miscellaneous | 2 | 1350 | 2700 |
| Lunch expenses | Miscellaneous | 3 | 1200 | 3600 |
| LCD | Equipment | 1 | 3000 | 3000 |
| keyboard | Equipment | 1 | 300 | 300 |
| mouse | Equipment | 1 | 120 | 120 |
| VGA to HDMI | Equipment | 1 | 850 | 850 |
| modem | Equipment | 1 | 1500 | 1500 |
| glue gun | Equipment | 1 | 300 | 300 |
| wire solder | Equipment | 1 | 450 | 450 |
| Documentation Printing | Miscellaneous | 1 | 440 | 440 |