The Technology of Self-Driving Cars
How do Self-Driving Cars Work
Tesla, Nissan, and google all claimed that within the next five years they will be able to produce a completely self-driving car. Self-driving cars require a GPS Unit, an internal navigation system and a ton of different sensors. This abundance of sensors usually include a camera sensor, radar sensor, and a later rangefinder sensor. These machines are used in unison to location the position of the car in three dimensions.
The Physics Behind the Speed
The car used all of its sensors and to plan a path two a specific destinations while following the rules of the road, and avoiding obstacles and cars. Different Cars have different sensors, and therefore gather different information, but the some basic information needs to be collected by all self-stopping cars such as speed, direction, and angular position. The car, uses physics allgorithims throughout the entire trip, has to calculate whether it is possible for a car, traveling at any certain speed, to be able to change lanes, take certain turns, and go down certain paths. A laser rangefinder scans the environment using laser beams and calculates the distance to nearby objects by measuring the time it takes for each laser beam to travel to the object and back. Laser rangefinders use that depth information for building a three-dimensional map. A vehicle’s internal map includes the current and predicted location of all static and moving obstacles in its vicinity. The vehicle uses a probabilistic model to track the predicted future path of moving objects based on its shape and prior trajectory. This process allows the vehicle to make decisions. For example, a vehicle traveling at 50 mph would not be able to safely complete a right turn 5 meters ahead, therefore that path would be eliminated from the feasible set. After evaluating feasible paths, the car can make safe decisions. Remaining paths are evaluated based on safety, speed, and any time requirements. Once the best path has been identified, a set of throttle, brake and steering commands, are passed on to the vehicle’s on-board processors and actuators. Altogether, this process takes on average 50ms, although it can be longer or shorter depending on the amount of collected data, available processing power, and complexity of the path planning algorithm.
Limitions
Car manufactures have made huge strives to create self-driving cars, but there are still large problems that stand in the way of the average American obtaining a self-driving car in the near future. Some of these issues include the unreliability of GPS maps, cars not know all of the different aspects of every road, weather condition, road detours, and other types of things that cannot yet be processed by a computer while driving. These limitations will be able to be overcome, but the self- driving will be slowly integrated into the average population. Many people will not be able to afford a self driving car for many years, and many of the self driving cars will not be completely, self-sufficent for many years to come.
Tesla, Nissan, and google all claimed that within the next five years they will be able to produce a completely self-driving car. Self-driving cars require a GPS Unit, an internal navigation system and a ton of different sensors. This abundance of sensors usually include a camera sensor, radar sensor, and a later rangefinder sensor. These machines are used in unison to location the position of the car in three dimensions.
The car used all of its sensors and to plan a path two a specific destinations while following the rules of the road, and avoiding obstacles and cars. Different Cars have different sensors, and therefore gather different information, but the some basic information needs to be collected by all self-stopping cars such as speed, direction, and angular position. The car, uses physics allgorithims throughout the entire trip, has to calculate whether it is possible for a car, traveling at any certain speed, to be able to change lanes, take certain turns, and go down certain paths. A laser rangefinder scans the environment using laser beams and calculates the distance to nearby objects by measuring the time it takes for each laser beam to travel to the object and back. Laser rangefinders use that depth information for building a three-dimensional map. A vehicle’s internal map includes the current and predicted location of all static and moving obstacles in its vicinity. The vehicle uses a probabilistic model to track the predicted future path of moving objects based on its shape and prior trajectory. This process allows the vehicle to make decisions. For example, a vehicle traveling at 50 mph would not be able to safely complete a right turn 5 meters ahead, therefore that path would be eliminated from the feasible set. After evaluating feasible paths, the car can make safe decisions. Remaining paths are evaluated based on safety, speed, and any time requirements. Once the best path has been identified, a set of throttle, brake and steering commands, are passed on to the vehicle’s on-board processors and actuators. Altogether, this process takes on average 50ms, although it can be longer or shorter depending on the amount of collected data, available processing power, and complexity of the path planning algorithm.
No comments:
Post a Comment