Machine Learning Model for Commuter Skateboard's Onboard Software
Question
You work for a robotics company that is building a new product that allows commuters to ride electric skateboards to work.
These skateboards are equipped with IoT sensors for safety measures.
The sensors detect obstacles in the path of the skateboard and alert the rider with haptics and sound.
The onboard software also uses the IoT sensor data to adjust the skateboard's performance based on its surroundings.
This allows the rider who follows similar paths to work on their daily commute to have their skateboard become more adept at handling the surroundings commonly encountered on this path. Which type of machine learning model would you use to build the onboard software for these commuter skateboards?
Answers
Explanations
Click on the arrows to vote for the correct answer
A. B. C. D.The type of machine learning model that would be suitable for the onboard software of the commuter skateboards is C. Reinforcement Learning model.
Reinforcement Learning (RL) is a type of machine learning model that deals with training an agent to take actions in an environment to maximize some notion of cumulative reward. In this scenario, the agent is the skateboard and the environment is the path to work. The skateboard's performance is adjusted based on its surroundings, which means that the agent must learn how to act in a changing environment, adapting to new obstacles and situations.
In this case, the IoT sensors detect obstacles and provide feedback to the rider through haptic and sound alerts. This feedback can be viewed as the reward signal in the RL model. The skateboard's actions can then be adjusted based on the received feedback, and the agent can learn to maximize the reward signal over time.
Furthermore, the onboard software needs to be able to learn from its surroundings to become more adept at handling obstacles commonly encountered on the rider's daily commute. Reinforcement learning can provide a way to adapt the agent's actions in response to changes in the environment. By learning from the feedback provided by the IoT sensors, the skateboard can become more adept at handling obstacles and providing a safer and smoother ride for the rider.
Therefore, the most appropriate machine learning model to use for building the onboard software for these commuter skateboards is a Reinforcement Learning model.
