Introduction: Markov Crawler

By plus.google.com/1122313500688659

Crawler can execute a reflex agent or Q-learn optimal policy using Markov decision process.

Raspberry Pi runs CS188 AI Python software controlling crawler 2 servo motors for arm and hand, acquiring crawler position from optical mouse.

Step 1: Overview of the Project

Attachments

Step 2: Assembly Instruction

Attachments

Step 3: Usage Instruction

Attachments

Step 4: Q-learning Process

https://youtu.be/Ex3Hbc69Aps

Step 5: Execution of Q-learned Policy

https://youtu.be/C7HSPhb4rQ4

Step 6: Synchronization of Simulator and Physical Robot

https://youtu.be/xYO9BCDn2AA