I don’t use this card, but looking at the docs, I think I see your problem:
You’re specifying a camera as the map_source, but then using an image entity. The demo config shows a camera.xiaomi_cloud_map_extractor entity being used:
Correct it pulls the info off the hot and stuff the detail in the map attributes. The card also CAN send a bot to a spot to clean if the cloud map extractor is installed and supports your bot.