Loading Now

Summary of Promptable Closed-loop Traffic Simulation, by Shuhan Tan et al.


Promptable Closed-loop Traffic Simulation

by Shuhan Tan, Boris Ivanovic, Yuxiao Chen, Boyi Li, Xinshuo Weng, Yulong Cao, Philipp Krähenbühl, Marco Pavone

First submitted to arxiv on: 9 Sep 2024

Categories

  • Main: Computer Vision and Pattern Recognition (cs.CV)
  • Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
A multimodal promptable closed-loop traffic simulation framework, ProSim, is proposed for autonomous driving development. It enables users to provide complex prompts, numerical, categorical, or textual, to instruct agents’ behaviors and intentions. The system simulates realistic, reactive, and controllable traffic patterns in a closed-loop manner, modeling each agent’s interactions with other traffic participants. Experiments show that ProSim achieves high prompt controllability while reaching competitive performance on the Waymo Sim Agents Challenge without prompts.
Low GrooveSquid.com (original content) Low Difficulty Summary
ProSim is a new tool for creating real-life traffic simulations. It lets users tell agents what to do and how to behave in different situations. The system makes traffic scenarios look realistic, and it can even change its behavior based on what’s happening around it. Researchers will find ProSim useful for studying how to make autonomous cars work better.

Keywords

» Artificial intelligence  » Prompt