DEVELOPMENT OF INTELLIGENT SELF-BALANCING E-BIKE USING MACHINE LEARNING

Abstract

The self-driving autonomous cars is becoming an increasingly popular concept all around the world but the area of self-driving two wheelers is still under developed. For developing countries like India, two wheelers are affordable than cars for most of the population. The project aims at developing intelligent self-balancing bike using artificial intelligence because the major problem in developing an autonomous bike is in the area of balancing. Even though there are many working mechanisms available for self-balancing of bike, the implementation of AI will be an edge over others from the point of computational power requirement and the programming complexity incurred. A prototype of the bike was developed with reaction wheel mechanism for self-balancing. The mechanism was fully controlled by AI by preventing the need of explicit programming for balancing which was the earlier technique used in self-balancing bike. Reinforcement learning, a type of machine learning technique is adopted for this purpose. The policy gradient algorithm was used to make the bike learn by itself for balancing. Even though the AI algorithm worked well in the virtual environment (balancing a cart-pole) it fails in the real environment. (i.e. it fails to balance the bike). It is because of the noisy data from the sensor, which gives inaccurate information about the orientation of the bike. The noise in the data is due to the vibration of the body when the reaction wheel rotates. This could be solved if the AI is fed with accurate information about the orientation of the vehicle.