search

Tsinghua-MARS-Lab / M2I

M2I is a simple but effective joint motion prediction framework through marginal and conditional predictions by exploiting the factorized relations between interacting agents.
https://tsinghua-mars-lab.github.io/M2I/
MIT License
187 stars 24 forks source link

What is the input for relation predictor? #2

Closed TianzhuQin closed 2 years ago

TianzhuQin commented 2 years ago

Hi, I am really looking forward to the code!

Before that, may I please ask what is the input for the relation predictor? Is it the whole graph, car's trajectory or any others?

Very Expect for your kind answer!

larksq commented 2 years ago

Hi TianZhu,

We use the same input as any typical trajectory predictor would use. These input data include the map, other agents' past trajectory with their infos (like shapes or types), and the traffic lights' states with their infos. More details can be found at this great repo of our backbone, the DenseTNT. In fact, we use exactly the same input as DenseTNT use.

Let me know if you have any further questions.

Qiao