Pragmatic Implementation of Reinforcement Algorithms For Path Finding On Raspberry Pi
This work addresses cost-efficient indoor delivery automation, but it is incremental as it applies existing reinforcement learning methods to a specific robotic setup.
The paper tackles indoor autonomous delivery by implementing Q-learning and Deep-Q learning on a Raspberry Pi-controlled robot for path planning and collision avoidance, achieving a proof-of-concept system that navigates the shortest path in a grid environment.
In this paper, pragmatic implementation of an indoor autonomous delivery system that exploits Reinforcement Learning algorithms for path planning and collision avoidance is audited. The proposed system is a cost-efficient approach that is implemented to facilitate a Raspberry Pi controlled four-wheel-drive non-holonomic robot map a grid. This approach computes and navigates the shortest path from a source key point to a destination key point to carry out the desired delivery. Q learning and Deep-Q learning are used to find the optimal path while avoiding collision with static obstacles. This work defines an approach to deploy these two algorithms on a robot. A novel algorithm to decode an array of directions into accurate movements in a certain action space is also proposed. The procedure followed to dispatch this system with the said requirements is described, ergo presenting our proof of concept for indoor autonomous delivery vehicles.